Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6120 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2204. Min Range: -6.2204
Max Act: 6.2204. Min Act: -0.1700
Data Index: 3091966 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2204. Min Range: -6.2204
Max Act: 6.1892. Min Act: -0.1700
Data Index: 6663719 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2204. Min Range: -6.2204
Max Act: 6.1892. Min Act: -0.1700
Data Index: 6643652 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2204. Min Range: -6.2204
Max Act: 6.1267. Min Act: -0.1700
Data Index: 48653 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2204. Min Range: -6.2204
Max Act: 6.0642. Min Act: -0.1700
Data Index: 2694508 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2204. Min Range: -6.2204
Max Act: 6.0954. Min Act: -0.1700
Data Index: 1045034 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2204. Min Range: -6.2204
Max Act: 6.0329. Min Act: -0.1700
Data Index: 8002035 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2204. Min Range: -6.2204
Max Act: 6.0017. Min Act: -0.1700
Data Index: 814572 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2204. Min Range: -6.2204
Max Act: 6.0329. Min Act: -0.1700
Data Index: 3772687 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2204. Min Range: -6.2204
Max Act: 6.0017. Min Act: -0.1700
Data Index: 5802717 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2204. Min Range: -6.2204
Max Act: 5.9392. Min Act: -0.1700
Data Index: 7089867 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2204. Min Range: -6.2204
Max Act: 5.9392. Min Act: -0.1700
Data Index: 2565459 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2204. Min Range: -6.2204
Max Act: 5.9392. Min Act: -0.1700
Data Index: 4508006 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2204. Min Range: -6.2204
Max Act: 5.8767. Min Act: -0.1700
Data Index: 4953062 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2204. Min Range: -6.2204
Max Act: 5.9079. Min Act: -0.1700
Data Index: 112104 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2204. Min Range: -6.2204
Max Act: 5.9079. Min Act: -0.1700
Data Index: 8290027 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2204. Min Range: -6.2204
Max Act: 5.9079. Min Act: -0.1700
Data Index: 7137509 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2204. Min Range: -6.2204
Max Act: 5.8767. Min Act: -0.1700
Data Index: 8078121 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2204. Min Range: -6.2204
Max Act: 5.8767. Min Act: -0.1700
Data Index: 5309199 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2204. Min Range: -6.2204
Max Act: 5.8454. Min Act: -0.1700
Data Index: 2601055 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19