Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3354 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3108. Min Range: -5.3108
Max Act: 5.3108. Min Act: -0.1700
Data Index: 1368629 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3108. Min Range: -5.3108
Max Act: 5.2171. Min Act: -0.1700
Data Index: 7695815 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3108. Min Range: -5.3108
Max Act: 5.1858. Min Act: -0.1700
Data Index: 719313 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3108. Min Range: -5.3108
Max Act: 5.1233. Min Act: -0.1700
Data Index: 4003866 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3108. Min Range: -5.3108
Max Act: 5.0921. Min Act: -0.1700
Data Index: 5454529 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3108. Min Range: -5.3108
Max Act: 5.0921. Min Act: -0.1700
Data Index: 4170687 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3108. Min Range: -5.3108
Max Act: 5.0921. Min Act: -0.1700
Data Index: 2357189 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3108. Min Range: -5.3108
Max Act: 5.0921. Min Act: -0.1700
Data Index: 6709280 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3108. Min Range: -5.3108
Max Act: 5.0608. Min Act: -0.1700
Data Index: 7231365 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3108. Min Range: -5.3108
Max Act: 5.0608. Min Act: -0.1700
Data Index: 3860327 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3108. Min Range: -5.3108
Max Act: 5.0608. Min Act: -0.1700
Data Index: 1141291 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3108. Min Range: -5.3108
Max Act: 5.0608. Min Act: -0.1699
Data Index: 8537220 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3108. Min Range: -5.3108
Max Act: 5.0608. Min Act: -0.1700
Data Index: 7964982 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3108. Min Range: -5.3108
Max Act: 5.0608. Min Act: -0.1700
Data Index: 7801679 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3108. Min Range: -5.3108
Max Act: 5.0608. Min Act: -0.1700
Data Index: 5996463 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3108. Min Range: -5.3108
Max Act: 5.0296. Min Act: -0.1700
Data Index: 7483830 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3108. Min Range: -5.3108
Max Act: 4.9983. Min Act: -0.1700
Data Index: 2546498 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3108. Min Range: -5.3108
Max Act: 4.9983. Min Act: -0.1700
Data Index: 7522556 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3108. Min Range: -5.3108
Max Act: 5.0296. Min Act: -0.1700
Data Index: 5285294 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3108. Min Range: -5.3108
Max Act: 5.0296. Min Act: -0.1700
Data Index: 5518110 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19