Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1937 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5310. Min Range: -3.5310
Max Act: 3.5310. Min Act: -0.1700
Data Index: 5697477 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5310. Min Range: -3.5310
Max Act: 3.5310. Min Act: -0.1700
Data Index: 2924022 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5310. Min Range: -3.5310
Max Act: 3.5310. Min Act: -0.1700
Data Index: 6698974 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5310. Min Range: -3.5310
Max Act: 3.5310. Min Act: -0.1700
Data Index: 2862776 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5310. Min Range: -3.5310
Max Act: 3.4997. Min Act: -0.1700
Data Index: 1552432 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5310. Min Range: -3.5310
Max Act: 3.4997. Min Act: -0.1700
Data Index: 798552 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5310. Min Range: -3.5310
Max Act: 3.4997. Min Act: -0.1700
Data Index: 5539849 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5310. Min Range: -3.5310
Max Act: 3.4997. Min Act: -0.1700
Data Index: 8607478 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5310. Min Range: -3.5310
Max Act: 3.4997. Min Act: -0.1700
Data Index: 7092457 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5310. Min Range: -3.5310
Max Act: 3.4684. Min Act: -0.1700
Data Index: 3912951 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5310. Min Range: -3.5310
Max Act: 3.4684. Min Act: -0.1700
Data Index: 3983563 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5310. Min Range: -3.5310
Max Act: 3.4684. Min Act: -0.1700
Data Index: 3871581 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5310. Min Range: -3.5310
Max Act: 3.4684. Min Act: -0.1700
Data Index: 61144 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5310. Min Range: -3.5310
Max Act: 3.4684. Min Act: -0.1700
Data Index: 4337087 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5310. Min Range: -3.5310
Max Act: 3.4684. Min Act: -0.1700
Data Index: 2229187 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5310. Min Range: -3.5310
Max Act: 3.4684. Min Act: -0.1700
Data Index: 3814873 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5310. Min Range: -3.5310
Max Act: 3.4684. Min Act: -0.1700
Data Index: 5839708 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5310. Min Range: -3.5310
Max Act: 3.4684. Min Act: -0.1700
Data Index: 3206636 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5310. Min Range: -3.5310
Max Act: 3.4684. Min Act: -0.1700
Data Index: 3215791 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5310. Min Range: -3.5310
Max Act: 3.4684. Min Act: -0.1700
Data Index: 188515 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19