Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4863 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9280. Min Range: -5.9280
Max Act: 5.9280. Min Act: -0.1697
Data Index: 6486658 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9280. Min Range: -5.9280
Max Act: 5.8968. Min Act: -0.1700
Data Index: 1474937 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9280. Min Range: -5.9280
Max Act: 5.7718. Min Act: -0.1700
Data Index: 6548053 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9280. Min Range: -5.9280
Max Act: 5.7718. Min Act: -0.1700
Data Index: 1016460 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9280. Min Range: -5.9280
Max Act: 5.7718. Min Act: -0.1700
Data Index: 8207671 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9280. Min Range: -5.9280
Max Act: 5.7093. Min Act: -0.1700
Data Index: 682116 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9280. Min Range: -5.9280
Max Act: 5.7093. Min Act: -0.1700
Data Index: 6399387 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9280. Min Range: -5.9280
Max Act: 5.6780. Min Act: -0.1700
Data Index: 8713846 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9280. Min Range: -5.9280
Max Act: 5.6780. Min Act: -0.1700
Data Index: 7889759 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9280. Min Range: -5.9280
Max Act: 5.6780. Min Act: -0.1700
Data Index: 7123338 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9280. Min Range: -5.9280
Max Act: 5.6780. Min Act: -0.1700
Data Index: 2596553 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9280. Min Range: -5.9280
Max Act: 5.6780. Min Act: -0.1700
Data Index: 5823212 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9280. Min Range: -5.9280
Max Act: 5.6468. Min Act: -0.1700
Data Index: 8622271 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9280. Min Range: -5.9280
Max Act: 5.6468. Min Act: -0.1699
Data Index: 5160375 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9280. Min Range: -5.9280
Max Act: 5.6468. Min Act: -0.1700
Data Index: 2583214 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9280. Min Range: -5.9280
Max Act: 5.6468. Min Act: -0.1700
Data Index: 1332768 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9280. Min Range: -5.9280
Max Act: 5.6155. Min Act: -0.1700
Data Index: 3932430 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9280. Min Range: -5.9280
Max Act: 5.6468. Min Act: -0.1700
Data Index: 1445638 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9280. Min Range: -5.9280
Max Act: 5.6468. Min Act: -0.1700
Data Index: 753439 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9280. Min Range: -5.9280
Max Act: 5.6155. Min Act: -0.1700
Data Index: 5154667 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19