Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 69 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9162. Min Range: -2.9162
Max Act: 2.9162. Min Act: -0.1700
Data Index: 4453128 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9162. Min Range: -2.9162
Max Act: 2.8845. Min Act: -0.1700
Data Index: 92302 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9162. Min Range: -2.9162
Max Act: 2.8686. Min Act: -0.1700
Data Index: 5701587 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9162. Min Range: -2.9162
Max Act: 2.8686. Min Act: -0.1700
Data Index: 6212592 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9162. Min Range: -2.9162
Max Act: 2.8686. Min Act: -0.1700
Data Index: 8155366 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9162. Min Range: -2.9162
Max Act: 2.8527. Min Act: -0.1700
Data Index: 403351 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9162. Min Range: -2.9162
Max Act: 2.8527. Min Act: -0.1700
Data Index: 1659453 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9162. Min Range: -2.9162
Max Act: 2.8368. Min Act: -0.1700
Data Index: 4055900 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9162. Min Range: -2.9162
Max Act: 2.8209. Min Act: -0.1700
Data Index: 862258 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9162. Min Range: -2.9162
Max Act: 2.8209. Min Act: -0.1700
Data Index: 6886382 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9162. Min Range: -2.9162
Max Act: 2.8050. Min Act: -0.1700
Data Index: 3275826 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9162. Min Range: -2.9162
Max Act: 2.8209. Min Act: -0.1700
Data Index: 8423775 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9162. Min Range: -2.9162
Max Act: 2.8209. Min Act: -0.1700
Data Index: 3615922 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9162. Min Range: -2.9162
Max Act: 2.8050. Min Act: -0.1700
Data Index: 5471043 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9162. Min Range: -2.9162
Max Act: 2.8050. Min Act: -0.1700
Data Index: 4271177 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9162. Min Range: -2.9162
Max Act: 2.8050. Min Act: -0.1700
Data Index: 3464964 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9162. Min Range: -2.9162
Max Act: 2.7891. Min Act: -0.1700
Data Index: 3405927 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9162. Min Range: -2.9162
Max Act: 2.8050. Min Act: -0.1700
Data Index: 4084484 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9162. Min Range: -2.9162
Max Act: 2.8050. Min Act: -0.1700
Data Index: 2566537 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9162. Min Range: -2.9162
Max Act: 2.8050. Min Act: -0.1700
Data Index: 2487430 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19