Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2525 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8378. Min Range: -5.8378
Max Act: 5.8378. Min Act: -0.1700
Data Index: 7589521 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8378. Min Range: -5.8378
Max Act: 5.6191. Min Act: -0.1700
Data Index: 5868377 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8378. Min Range: -5.8378
Max Act: 5.4003. Min Act: -0.1700
Data Index: 6020174 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8378. Min Range: -5.8378
Max Act: 5.4003. Min Act: -0.1700
Data Index: 2544437 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8378. Min Range: -5.8378
Max Act: 5.2753. Min Act: -0.1700
Data Index: 6755377 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8378. Min Range: -5.8378
Max Act: 5.2753. Min Act: -0.1700
Data Index: 5889580 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8378. Min Range: -5.8378
Max Act: 5.1191. Min Act: -0.1700
Data Index: 2286581 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8378. Min Range: -5.8378
Max Act: 5.1191. Min Act: -0.1700
Data Index: 3268465 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8378. Min Range: -5.8378
Max Act: 5.1191. Min Act: -0.1700
Data Index: 7453988 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8378. Min Range: -5.8378
Max Act: 5.1191. Min Act: -0.1700
Data Index: 3401589 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8378. Min Range: -5.8378
Max Act: 5.0566. Min Act: -0.1700
Data Index: 4447283 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8378. Min Range: -5.8378
Max Act: 5.0878. Min Act: -0.1700
Data Index: 4954689 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8378. Min Range: -5.8378
Max Act: 5.0566. Min Act: -0.1700
Data Index: 439554 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8378. Min Range: -5.8378
Max Act: 5.0566. Min Act: -0.1700
Data Index: 4173771 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8378. Min Range: -5.8378
Max Act: 5.0566. Min Act: -0.1700
Data Index: 25915 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8378. Min Range: -5.8378
Max Act: 5.0253. Min Act: -0.1700
Data Index: 2650776 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8378. Min Range: -5.8378
Max Act: 5.0253. Min Act: -0.1700
Data Index: 4458694 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8378. Min Range: -5.8378
Max Act: 5.0253. Min Act: -0.1700
Data Index: 280952 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8378. Min Range: -5.8378
Max Act: 4.9941. Min Act: -0.1700
Data Index: 4734183 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8378. Min Range: -5.8378
Max Act: 5.0253. Min Act: -0.1700
Data Index: 4815090 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19