Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1143 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.5472. Min Act: -0.1700
Data Index: 4341449 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.4847. Min Act: -0.1700
Data Index: 2517354 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.5160. Min Act: -0.1700
Data Index: 4422522 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.4222. Min Act: -0.1700
Data Index: 623125 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.4222. Min Act: -0.1700
Data Index: 4086533 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.3910. Min Act: -0.1700
Data Index: 944428 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.3910. Min Act: -0.1700
Data Index: 3386189 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.3910. Min Act: -0.1700
Data Index: 8191977 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.3597. Min Act: -0.1700
Data Index: 3371603 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.3597. Min Act: -0.1700
Data Index: 390624 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.3597. Min Act: -0.1700
Data Index: 2891568 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.3285. Min Act: -0.1700
Data Index: 6275544 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.3285. Min Act: -0.1700
Data Index: 246916 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.3285. Min Act: -0.1700
Data Index: 7064904 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2972. Min Act: -0.1700
Data Index: 3371202 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2972. Min Act: -0.1700
Data Index: 5525602 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2972. Min Act: -0.1700
Data Index: 5086248 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2972. Min Act: -0.1700
Data Index: 7799052 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2972. Min Act: -0.1700
Data Index: 189701 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.3285. Min Act: -0.1700
Data Index: 2249308 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19