Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3029 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2042. Min Range: -3.2042
Max Act: 3.2042. Min Act: -0.1700
Data Index: 2830294 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2042. Min Range: -3.2042
Max Act: 3.1570. Min Act: -0.1700
Data Index: 2045321 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2042. Min Range: -3.2042
Max Act: 2.9993. Min Act: -0.1700
Data Index: 76698 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2042. Min Range: -3.2042
Max Act: 2.9360. Min Act: -0.1700
Data Index: 5304992 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2042. Min Range: -3.2042
Max Act: 2.9360. Min Act: -0.1700
Data Index: 437408 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2042. Min Range: -3.2042
Max Act: 2.9043. Min Act: -0.1700
Data Index: 620628 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2042. Min Range: -3.2042
Max Act: 2.9201. Min Act: -0.1700
Data Index: 1201374 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2042. Min Range: -3.2042
Max Act: 2.8884. Min Act: -0.1700
Data Index: 3723473 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2042. Min Range: -3.2042
Max Act: 2.8884. Min Act: -0.1700
Data Index: 3363585 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2042. Min Range: -3.2042
Max Act: 2.8884. Min Act: -0.1700
Data Index: 5703547 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2042. Min Range: -3.2042
Max Act: 2.8567. Min Act: -0.1700
Data Index: 501963 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2042. Min Range: -3.2042
Max Act: 2.8567. Min Act: -0.1700
Data Index: 8277616 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2042. Min Range: -3.2042
Max Act: 2.8408. Min Act: -0.1700
Data Index: 8277618 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2042. Min Range: -3.2042
Max Act: 2.8249. Min Act: -0.1700
Data Index: 8047828 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2042. Min Range: -3.2042
Max Act: 2.7930. Min Act: -0.1700
Data Index: 6809376 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2042. Min Range: -3.2042
Max Act: 2.7930. Min Act: -0.1700
Data Index: 8529677 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2042. Min Range: -3.2042
Max Act: 2.7612. Min Act: -0.1700
Data Index: 5831144 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2042. Min Range: -3.2042
Max Act: 2.7771. Min Act: -0.1700
Data Index: 2520048 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2042. Min Range: -3.2042
Max Act: 2.7292. Min Act: -0.1700
Data Index: 2736070 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2042. Min Range: -3.2042
Max Act: 2.7452. Min Act: -0.1700
Data Index: 2315299 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19