Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2582 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9189. Min Range: -6.9189
Max Act: 6.9189. Min Act: -0.1700
Data Index: 7266893 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9189. Min Range: -6.9189
Max Act: 6.6689. Min Act: -0.1700
Data Index: 1251335 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9189. Min Range: -6.9189
Max Act: 6.6064. Min Act: -0.1700
Data Index: 3421825 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9189. Min Range: -6.9189
Max Act: 6.5439. Min Act: -0.1700
Data Index: 7677212 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9189. Min Range: -6.9189
Max Act: 6.5439. Min Act: -0.1700
Data Index: 1436815 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9189. Min Range: -6.9189
Max Act: 6.5126. Min Act: -0.1700
Data Index: 8372410 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9189. Min Range: -6.9189
Max Act: 6.5126. Min Act: -0.1700
Data Index: 6892561 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9189. Min Range: -6.9189
Max Act: 6.4501. Min Act: -0.1700
Data Index: 2478487 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9189. Min Range: -6.9189
Max Act: 6.4814. Min Act: -0.1700
Data Index: 5019593 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9189. Min Range: -6.9189
Max Act: 6.4501. Min Act: -0.1700
Data Index: 2789025 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9189. Min Range: -6.9189
Max Act: 6.4501. Min Act: -0.1700
Data Index: 7847230 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9189. Min Range: -6.9189
Max Act: 6.4189. Min Act: -0.1700
Data Index: 378927 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9189. Min Range: -6.9189
Max Act: 6.3876. Min Act: -0.1700
Data Index: 5247835 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9189. Min Range: -6.9189
Max Act: 6.4189. Min Act: -0.1700
Data Index: 8471205 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9189. Min Range: -6.9189
Max Act: 6.3876. Min Act: -0.1700
Data Index: 5243942 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9189. Min Range: -6.9189
Max Act: 6.3876. Min Act: -0.1700
Data Index: 6461745 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9189. Min Range: -6.9189
Max Act: 6.3876. Min Act: -0.1700
Data Index: 8578380 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9189. Min Range: -6.9189
Max Act: 6.3876. Min Act: -0.1700
Data Index: 377996 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9189. Min Range: -6.9189
Max Act: 6.3251. Min Act: -0.1700
Data Index: 7797351 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9189. Min Range: -6.9189
Max Act: 6.3251. Min Act: -0.1700
Data Index: 6904749 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19