Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1282 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.8905. Min Act: -0.1700
Data Index: 8611673 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.8593. Min Act: -0.1700
Data Index: 880067 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.8593. Min Act: -0.1700
Data Index: 1523178 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.7968. Min Act: -0.1700
Data Index: 61305 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.7343. Min Act: -0.1700
Data Index: 3043004 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.6718. Min Act: -0.1700
Data Index: 3875611 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.6405. Min Act: -0.1700
Data Index: 7067393 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.6405. Min Act: -0.1700
Data Index: 7963516 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.6718. Min Act: -0.1700
Data Index: 8268193 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.6093. Min Act: -0.1700
Data Index: 5800061 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.6093. Min Act: -0.1700
Data Index: 6640177 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.6405. Min Act: -0.1700
Data Index: 3996884 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.6093. Min Act: -0.1700
Data Index: 2318716 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.5468. Min Act: -0.1700
Data Index: 2547504 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.5780. Min Act: -0.1700
Data Index: 381447 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.5780. Min Act: -0.1700
Data Index: 6056538 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.5468. Min Act: -0.1700
Data Index: 2008425 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.5468. Min Act: -0.1700
Data Index: 4663728 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.5155. Min Act: -0.1700
Data Index: 8268192 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8905. Min Range: -5.8905
Max Act: 5.5155. Min Act: -0.1700
Data Index: 2703834 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19