Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3091 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7237. Min Range: -6.7237
Max Act: 6.7237. Min Act: -0.1700
Data Index: 5949176 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7237. Min Range: -6.7237
Max Act: 6.6612. Min Act: -0.1700
Data Index: 7466751 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7237. Min Range: -6.7237
Max Act: 6.5362. Min Act: -0.1700
Data Index: 4485682 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7237. Min Range: -6.7237
Max Act: 6.5049. Min Act: -0.1700
Data Index: 1119164 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7237. Min Range: -6.7237
Max Act: 6.4737. Min Act: -0.1700
Data Index: 3647105 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7237. Min Range: -6.7237
Max Act: 6.4424. Min Act: -0.1700
Data Index: 5310059 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7237. Min Range: -6.7237
Max Act: 6.3487. Min Act: -0.1700
Data Index: 2847240 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7237. Min Range: -6.7237
Max Act: 6.2549. Min Act: -0.1700
Data Index: 3982445 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7237. Min Range: -6.7237
Max Act: 6.2237. Min Act: -0.1700
Data Index: 963120 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7237. Min Range: -6.7237
Max Act: 6.2237. Min Act: -0.1700
Data Index: 3388511 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7237. Min Range: -6.7237
Max Act: 6.1924. Min Act: -0.1700
Data Index: 2298428 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7237. Min Range: -6.7237
Max Act: 6.1924. Min Act: -0.1700
Data Index: 4151969 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7237. Min Range: -6.7237
Max Act: 6.1612. Min Act: -0.1700
Data Index: 359301 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7237. Min Range: -6.7237
Max Act: 6.1612. Min Act: -0.1700
Data Index: 2918962 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7237. Min Range: -6.7237
Max Act: 6.0987. Min Act: -0.1700
Data Index: 543957 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7237. Min Range: -6.7237
Max Act: 6.0987. Min Act: -0.1700
Data Index: 6427461 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7237. Min Range: -6.7237
Max Act: 6.0674. Min Act: -0.1700
Data Index: 46031 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7237. Min Range: -6.7237
Max Act: 6.0674. Min Act: -0.1700
Data Index: 306226 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7237. Min Range: -6.7237
Max Act: 6.0674. Min Act: -0.1700
Data Index: 8317315 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7237. Min Range: -6.7237
Max Act: 6.0362. Min Act: -0.1700
Data Index: 1166604 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19