Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3197 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2192. Min Range: -5.2192
Max Act: 5.2192. Min Act: -0.1700
Data Index: 3054944 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2192. Min Range: -5.2192
Max Act: 5.1567. Min Act: -0.1700
Data Index: 2746269 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2192. Min Range: -5.2192
Max Act: 5.0317. Min Act: -0.1700
Data Index: 315697 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2192. Min Range: -5.2192
Max Act: 4.9692. Min Act: -0.1700
Data Index: 8484571 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2192. Min Range: -5.2192
Max Act: 4.9379. Min Act: -0.1700
Data Index: 2982968 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2192. Min Range: -5.2192
Max Act: 4.9379. Min Act: -0.1700
Data Index: 8420105 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2192. Min Range: -5.2192
Max Act: 4.9067. Min Act: -0.1700
Data Index: 4824609 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2192. Min Range: -5.2192
Max Act: 4.8754. Min Act: -0.1700
Data Index: 5418878 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2192. Min Range: -5.2192
Max Act: 4.8754. Min Act: -0.1700
Data Index: 5445255 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2192. Min Range: -5.2192
Max Act: 4.8442. Min Act: -0.1700
Data Index: 2622336 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2192. Min Range: -5.2192
Max Act: 4.8754. Min Act: -0.1700
Data Index: 5059874 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2192. Min Range: -5.2192
Max Act: 4.8442. Min Act: -0.1700
Data Index: 1392835 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2192. Min Range: -5.2192
Max Act: 4.8442. Min Act: -0.1700
Data Index: 4877105 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2192. Min Range: -5.2192
Max Act: 4.8442. Min Act: -0.1700
Data Index: 5158567 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2192. Min Range: -5.2192
Max Act: 4.8129. Min Act: -0.1700
Data Index: 202417 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2192. Min Range: -5.2192
Max Act: 4.8129. Min Act: -0.1700
Data Index: 1798399 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2192. Min Range: -5.2192
Max Act: 4.8129. Min Act: -0.1700
Data Index: 1907923 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2192. Min Range: -5.2192
Max Act: 4.8129. Min Act: -0.1700
Data Index: 8328059 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2192. Min Range: -5.2192
Max Act: 4.7817. Min Act: -0.1700
Data Index: 5724514 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2192. Min Range: -5.2192
Max Act: 4.7817. Min Act: -0.1700
Data Index: 4098927 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19