Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2285 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2214. Min Range: -4.2214
Max Act: 4.2214. Min Act: -0.1700
Data Index: 1165953 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2214. Min Range: -4.2214
Max Act: 4.0026. Min Act: -0.1700
Data Index: 4743571 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.9401. Min Act: -0.1700
Data Index: 4976289 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.8150. Min Act: -0.1700
Data Index: 628335 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.8150. Min Act: -0.1700
Data Index: 7515525 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.7837. Min Act: -0.1700
Data Index: 6196846 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.7837. Min Act: -0.1700
Data Index: 1267932 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.7525. Min Act: -0.1700
Data Index: 1149338 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.7212. Min Act: -0.1700
Data Index: 2030292 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.7837. Min Act: -0.1700
Data Index: 6845541 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.7525. Min Act: -0.1700
Data Index: 4949803 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.7525. Min Act: -0.1700
Data Index: 2712200 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.7212. Min Act: -0.1700
Data Index: 8067790 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.7212. Min Act: -0.1700
Data Index: 2235773 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.7212. Min Act: -0.1700
Data Index: 6027559 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.7212. Min Act: -0.1700
Data Index: 8176584 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.6899. Min Act: -0.1700
Data Index: 2954996 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.6743. Min Act: -0.1700
Data Index: 2581922 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.6743. Min Act: -0.1700
Data Index: 3016470 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.6899. Min Act: -0.1700
Data Index: 2052333 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19