Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5300 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4462. Min Range: -3.4462
Max Act: 3.4462. Min Act: -0.1700
Data Index: 270929 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4462. Min Range: -3.4462
Max Act: 3.3364. Min Act: -0.1700
Data Index: 1094474 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4462. Min Range: -3.4462
Max Act: 3.3207. Min Act: -0.1700
Data Index: 3222320 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4462. Min Range: -3.4462
Max Act: 3.2893. Min Act: -0.1700
Data Index: 6956801 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4462. Min Range: -3.4462
Max Act: 3.2736. Min Act: -0.1700
Data Index: 4422268 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4462. Min Range: -3.4462
Max Act: 3.2736. Min Act: -0.1700
Data Index: 3716112 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4462. Min Range: -3.4462
Max Act: 3.2422. Min Act: -0.1700
Data Index: 7715125 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4462. Min Range: -3.4462
Max Act: 3.2422. Min Act: -0.1700
Data Index: 1543377 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4462. Min Range: -3.4462
Max Act: 3.2265. Min Act: -0.1700
Data Index: 4291089 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4462. Min Range: -3.4462
Max Act: 3.2265. Min Act: -0.1700
Data Index: 750133 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4462. Min Range: -3.4462
Max Act: 3.2422. Min Act: -0.1700
Data Index: 2910814 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4462. Min Range: -3.4462
Max Act: 3.2108. Min Act: -0.1700
Data Index: 3903707 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4462. Min Range: -3.4462
Max Act: 3.2108. Min Act: -0.1700
Data Index: 1762854 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4462. Min Range: -3.4462
Max Act: 3.2108. Min Act: -0.1700
Data Index: 1293706 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4462. Min Range: -3.4462
Max Act: 3.2265. Min Act: -0.1700
Data Index: 6760491 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4462. Min Range: -3.4462
Max Act: 3.1951. Min Act: -0.1700
Data Index: 8645942 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4462. Min Range: -3.4462
Max Act: 3.1951. Min Act: -0.1700
Data Index: 3707494 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4462. Min Range: -3.4462
Max Act: 3.1793. Min Act: -0.1700
Data Index: 5627634 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4462. Min Range: -3.4462
Max Act: 3.2108. Min Act: -0.1700
Data Index: 3796872 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4462. Min Range: -3.4462
Max Act: 3.1951. Min Act: -0.1700
Data Index: 5337248 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19