Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3212 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7855. Min Range: -3.7855
Max Act: 3.7855. Min Act: -0.1700
Data Index: 4580524 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7855. Min Range: -3.7855
Max Act: 3.7855. Min Act: -0.1700
Data Index: 8537431 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7855. Min Range: -3.7855
Max Act: 3.7855. Min Act: -0.1700
Data Index: 8028524 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7855. Min Range: -3.7855
Max Act: 3.7543. Min Act: -0.1700
Data Index: 4335575 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7855. Min Range: -3.7855
Max Act: 3.7230. Min Act: -0.1700
Data Index: 6277009 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7855. Min Range: -3.7855
Max Act: 3.7230. Min Act: -0.1700
Data Index: 2505417 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7855. Min Range: -3.7855
Max Act: 3.7230. Min Act: -0.1700
Data Index: 4953691 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7855. Min Range: -3.7855
Max Act: 3.6917. Min Act: -0.1700
Data Index: 4968695 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7855. Min Range: -3.7855
Max Act: 3.6917. Min Act: -0.1700
Data Index: 2564287 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7855. Min Range: -3.7855
Max Act: 3.6291. Min Act: -0.1700
Data Index: 3368925 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7855. Min Range: -3.7855
Max Act: 3.6291. Min Act: -0.1700
Data Index: 3084774 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7855. Min Range: -3.7855
Max Act: 3.6291. Min Act: -0.1700
Data Index: 7076828 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7855. Min Range: -3.7855
Max Act: 3.6291. Min Act: -0.1700
Data Index: 2855178 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7855. Min Range: -3.7855
Max Act: 3.6291. Min Act: -0.1700
Data Index: 7265707 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7855. Min Range: -3.7855
Max Act: 3.6291. Min Act: -0.1700
Data Index: 1435482 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7855. Min Range: -3.7855
Max Act: 3.5978. Min Act: -0.1700
Data Index: 5619682 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7855. Min Range: -3.7855
Max Act: 3.6291. Min Act: -0.1700
Data Index: 4544613 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7855. Min Range: -3.7855
Max Act: 3.6291. Min Act: -0.1700
Data Index: 3831505 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7855. Min Range: -3.7855
Max Act: 3.5978. Min Act: -0.1700
Data Index: 1338247 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7855. Min Range: -3.7855
Max Act: 3.5978. Min Act: -0.1700
Data Index: 3086423 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19