Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1425 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.3962. Min Act: -0.1700
Data Index: 1578723 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.3962. Min Act: -0.1700
Data Index: 1948642 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.3649. Min Act: -0.1700
Data Index: 8351207 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.3649. Min Act: -0.1700
Data Index: 1533838 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.3337. Min Act: -0.1700
Data Index: 3746372 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.3337. Min Act: -0.1700
Data Index: 8177420 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.3024. Min Act: -0.1700
Data Index: 1249171 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.3024. Min Act: -0.1700
Data Index: 5889825 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.2712. Min Act: -0.1700
Data Index: 2507273 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.2399. Min Act: -0.1700
Data Index: 4403529 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.2087. Min Act: -0.1700
Data Index: 8497155 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.2399. Min Act: -0.1700
Data Index: 6765471 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.2087. Min Act: -0.1700
Data Index: 4596430 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.1774. Min Act: -0.1700
Data Index: 734908 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.1774. Min Act: -0.1700
Data Index: 8406391 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.1774. Min Act: -0.1700
Data Index: 3520473 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.1774. Min Act: -0.1700
Data Index: 8573310 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.1774. Min Act: -0.1700
Data Index: 6764364 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.1774. Min Act: -0.1700
Data Index: 8573309 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.1462. Min Act: -0.1700
Data Index: 4189795 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19