Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5111 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.9323. Min Act: -0.1700
Data Index: 3731971 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.5885. Min Act: -0.1700
Data Index: 677002 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.5260. Min Act: -0.1700
Data Index: 1640643 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.4010. Min Act: -0.1700
Data Index: 1154603 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.4010. Min Act: -0.1700
Data Index: 436346 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.4010. Min Act: -0.1700
Data Index: 8019952 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.3698. Min Act: -0.1700
Data Index: 6866733 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.3698. Min Act: -0.1700
Data Index: 6866732 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.3385. Min Act: -0.1700
Data Index: 3467938 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.3385. Min Act: -0.1700
Data Index: 325938 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.3385. Min Act: -0.1700
Data Index: 7520895 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.3073. Min Act: -0.1700
Data Index: 7134492 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.3073. Min Act: -0.1700
Data Index: 7859226 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.2760. Min Act: -0.1700
Data Index: 6540889 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.2760. Min Act: -0.1700
Data Index: 492188 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.2760. Min Act: -0.1700
Data Index: 6828318 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.2760. Min Act: -0.1700
Data Index: 7491365 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.2448. Min Act: -0.1700
Data Index: 4828055 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.2448. Min Act: -0.1700
Data Index: 6092796 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.2135. Min Act: -0.1700
Data Index: 3497615 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19