Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4992 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7554. Min Range: -4.7554
Max Act: 4.7554. Min Act: -0.1700
Data Index: 84454 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7554. Min Range: -4.7554
Max Act: 4.3804. Min Act: -0.1700
Data Index: 7487884 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7554. Min Range: -4.7554
Max Act: 4.2241. Min Act: -0.1700
Data Index: 7804402 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7554. Min Range: -4.7554
Max Act: 4.0991. Min Act: -0.1700
Data Index: 377426 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7554. Min Range: -4.7554
Max Act: 4.0678. Min Act: -0.1700
Data Index: 3530166 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7554. Min Range: -4.7554
Max Act: 4.0366. Min Act: -0.1700
Data Index: 4922096 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7554. Min Range: -4.7554
Max Act: 3.9740. Min Act: -0.1700
Data Index: 7476453 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7554. Min Range: -4.7554
Max Act: 3.9428. Min Act: -0.1700
Data Index: 4661951 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7554. Min Range: -4.7554
Max Act: 3.9428. Min Act: -0.1700
Data Index: 1625987 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7554. Min Range: -4.7554
Max Act: 3.8803. Min Act: -0.1700
Data Index: 1489349 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7554. Min Range: -4.7554
Max Act: 3.8490. Min Act: -0.1700
Data Index: 8610945 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7554. Min Range: -4.7554
Max Act: 3.8490. Min Act: -0.1700
Data Index: 7199720 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7554. Min Range: -4.7554
Max Act: 3.8177. Min Act: -0.1700
Data Index: 6936634 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7554. Min Range: -4.7554
Max Act: 3.8177. Min Act: -0.1700
Data Index: 8596399 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7554. Min Range: -4.7554
Max Act: 3.8177. Min Act: -0.1700
Data Index: 5340663 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7554. Min Range: -4.7554
Max Act: 3.7864. Min Act: -0.1700
Data Index: 3840301 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7554. Min Range: -4.7554
Max Act: 3.7864. Min Act: -0.1700
Data Index: 165491 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7554. Min Range: -4.7554
Max Act: 3.7864. Min Act: -0.1700
Data Index: 1847456 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7554. Min Range: -4.7554
Max Act: 3.7552. Min Act: -0.1700
Data Index: 8314737 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7554. Min Range: -4.7554
Max Act: 3.7864. Min Act: -0.1700
Data Index: 1698102 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19