Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3545 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8772. Min Range: -7.8772
Max Act: 7.8772. Min Act: -0.1700
Data Index: 1603229 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8772. Min Range: -7.8772
Max Act: 7.8772. Min Act: -0.1700
Data Index: 8152069 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8772. Min Range: -7.8772
Max Act: 7.8772. Min Act: -0.1700
Data Index: 5394178 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8772. Min Range: -7.8772
Max Act: 7.7522. Min Act: -0.1700
Data Index: 1070585 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8772. Min Range: -7.8772
Max Act: 7.7522. Min Act: -0.1700
Data Index: 7812564 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8772. Min Range: -7.8772
Max Act: 7.7522. Min Act: -0.1700
Data Index: 243948 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8772. Min Range: -7.8772
Max Act: 7.6897. Min Act: -0.1700
Data Index: 8006149 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8772. Min Range: -7.8772
Max Act: 7.6897. Min Act: -0.1700
Data Index: 1665297 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8772. Min Range: -7.8772
Max Act: 7.6584. Min Act: -0.1700
Data Index: 4872564 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8772. Min Range: -7.8772
Max Act: 7.6272. Min Act: -0.1700
Data Index: 3123759 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8772. Min Range: -7.8772
Max Act: 7.6272. Min Act: -0.1700
Data Index: 5430679 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8772. Min Range: -7.8772
Max Act: 7.5334. Min Act: -0.1700
Data Index: 4151062 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8772. Min Range: -7.8772
Max Act: 7.5022. Min Act: -0.1700
Data Index: 1364623 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8772. Min Range: -7.8772
Max Act: 7.5022. Min Act: -0.1700
Data Index: 3942119 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8772. Min Range: -7.8772
Max Act: 7.5022. Min Act: -0.1700
Data Index: 8022896 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8772. Min Range: -7.8772
Max Act: 7.4709. Min Act: -0.1700
Data Index: 143442 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8772. Min Range: -7.8772
Max Act: 7.4397. Min Act: -0.1700
Data Index: 4934702 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8772. Min Range: -7.8772
Max Act: 7.4084. Min Act: -0.1700
Data Index: 7527662 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8772. Min Range: -7.8772
Max Act: 7.3772. Min Act: -0.1700
Data Index: 7974598 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8772. Min Range: -7.8772
Max Act: 7.4084. Min Act: -0.1700
Data Index: 6912550 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19