Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 761 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2120. Min Range: -3.2120
Max Act: 3.2120. Min Act: -0.1700
Data Index: 759520 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2120. Min Range: -3.2120
Max Act: 3.2120. Min Act: -0.1700
Data Index: 7945932 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2120. Min Range: -3.2120
Max Act: 3.1806. Min Act: -0.1700
Data Index: 8393786 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2120. Min Range: -3.2120
Max Act: 3.1648. Min Act: -0.1700
Data Index: 2984726 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2120. Min Range: -3.2120
Max Act: 3.1648. Min Act: -0.1700
Data Index: 2439186 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2120. Min Range: -3.2120
Max Act: 3.1018. Min Act: -0.1700
Data Index: 6086679 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2120. Min Range: -3.2120
Max Act: 3.0703. Min Act: -0.1700
Data Index: 5628861 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2120. Min Range: -3.2120
Max Act: 3.0703. Min Act: -0.1700
Data Index: 1428546 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2120. Min Range: -3.2120
Max Act: 3.0703. Min Act: -0.1700
Data Index: 6656100 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2120. Min Range: -3.2120
Max Act: 3.0230. Min Act: -0.1700
Data Index: 3368347 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2120. Min Range: -3.2120
Max Act: 3.0388. Min Act: -0.1700
Data Index: 1759951 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2120. Min Range: -3.2120
Max Act: 3.0072. Min Act: -0.1700
Data Index: 1201227 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2120. Min Range: -3.2120
Max Act: 3.0072. Min Act: -0.1700
Data Index: 150654 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2120. Min Range: -3.2120
Max Act: 2.9914. Min Act: -0.1700
Data Index: 7133776 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2120. Min Range: -3.2120
Max Act: 2.9914. Min Act: -0.1700
Data Index: 5723623 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2120. Min Range: -3.2120
Max Act: 2.9755. Min Act: -0.1700
Data Index: 7119738 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2120. Min Range: -3.2120
Max Act: 2.9597. Min Act: -0.1700
Data Index: 6639983 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2120. Min Range: -3.2120
Max Act: 2.9597. Min Act: -0.1700
Data Index: 4371889 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2120. Min Range: -3.2120
Max Act: 2.9281. Min Act: -0.1700
Data Index: 8308607 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2120. Min Range: -3.2120
Max Act: 2.9439. Min Act: -0.1700
Data Index: 7543646 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19