Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5981 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 17.8263. Min Range: -17.8263
Max Act: 17.7013. Min Act: -0.1700
Data Index: 6698036 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 17.8263. Min Range: -17.8263
Max Act: 17.8263. Min Act: -0.1700
Data Index: 5973898 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 17.8263. Min Range: -17.8263
Max Act: 17.5763. Min Act: -0.1699
Data Index: 6564190 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 17.8263. Min Range: -17.8263
Max Act: 17.4513. Min Act: -0.1698
Data Index: 6031772 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 17.8263. Min Range: -17.8263
Max Act: 17.3263. Min Act: -0.1700
Data Index: 5423738 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 17.8263. Min Range: -17.8263
Max Act: 17.2013. Min Act: -0.1698
Data Index: 2228285 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 17.8263. Min Range: -17.8263
Max Act: 17.0763. Min Act: -0.1697
Data Index: 6698039 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 17.8263. Min Range: -17.8263
Max Act: 16.9513. Min Act: -0.1700
Data Index: 4094454 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 17.8263. Min Range: -17.8263
Max Act: 16.8263. Min Act: -0.1700
Data Index: 4768199 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 17.8263. Min Range: -17.8263
Max Act: 16.7013. Min Act: -0.1700
Data Index: 5973896 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 17.8263. Min Range: -17.8263
Max Act: 16.8263. Min Act: -0.1699
Data Index: 1148822 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 17.8263. Min Range: -17.8263
Max Act: 16.8263. Min Act: -0.1700
Data Index: 1460575 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 17.8263. Min Range: -17.8263
Max Act: 16.6388. Min Act: -0.1700
Data Index: 1460570 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 17.8263. Min Range: -17.8263
Max Act: 16.6388. Min Act: -0.1700
Data Index: 7379102 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 17.8263. Min Range: -17.8263
Max Act: 16.6388. Min Act: -0.1699
Data Index: 6698037 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 17.8263. Min Range: -17.8263
Max Act: 16.5763. Min Act: -0.1700
Data Index: 7087733 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 17.8263. Min Range: -17.8263
Max Act: 16.4513. Min Act: -0.1700
Data Index: 4094457 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 17.8263. Min Range: -17.8263
Max Act: 16.4513. Min Act: -0.1700
Data Index: 2655431 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 17.8263. Min Range: -17.8263
Max Act: 16.3888. Min Act: -0.1700
Data Index: 5423735 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 17.8263. Min Range: -17.8263
Max Act: 16.5138. Min Act: -0.1677
Data Index: 8669349 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19