Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4696 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5172. Min Range: -3.5172
Max Act: 3.5172. Min Act: -0.1700
Data Index: 6479685 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5172. Min Range: -3.5172
Max Act: 3.4388. Min Act: -0.1700
Data Index: 8117979 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5172. Min Range: -3.5172
Max Act: 3.3291. Min Act: -0.1700
Data Index: 2256465 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5172. Min Range: -3.5172
Max Act: 3.2506. Min Act: -0.1700
Data Index: 4914159 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5172. Min Range: -3.5172
Max Act: 3.2034. Min Act: -0.1700
Data Index: 2731630 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5172. Min Range: -3.5172
Max Act: 3.2034. Min Act: -0.1700
Data Index: 4894681 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5172. Min Range: -3.5172
Max Act: 3.1405. Min Act: -0.1700
Data Index: 5788795 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5172. Min Range: -3.5172
Max Act: 3.1405. Min Act: -0.1700
Data Index: 7475568 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5172. Min Range: -3.5172
Max Act: 3.1247. Min Act: -0.1700
Data Index: 8322231 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5172. Min Range: -3.5172
Max Act: 3.1405. Min Act: -0.1700
Data Index: 131442 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5172. Min Range: -3.5172
Max Act: 3.1090. Min Act: -0.1700
Data Index: 7376569 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5172. Min Range: -3.5172
Max Act: 3.1090. Min Act: -0.1700
Data Index: 3725059 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5172. Min Range: -3.5172
Max Act: 3.1090. Min Act: -0.1700
Data Index: 1321594 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5172. Min Range: -3.5172
Max Act: 3.1090. Min Act: -0.1700
Data Index: 6025402 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5172. Min Range: -3.5172
Max Act: 3.0932. Min Act: -0.1700
Data Index: 6236800 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5172. Min Range: -3.5172
Max Act: 3.1090. Min Act: -0.1700
Data Index: 5601978 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5172. Min Range: -3.5172
Max Act: 3.0774. Min Act: -0.1700
Data Index: 7276857 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5172. Min Range: -3.5172
Max Act: 3.0774. Min Act: -0.1700
Data Index: 4514247 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5172. Min Range: -3.5172
Max Act: 3.0617. Min Act: -0.1700
Data Index: 648147 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5172. Min Range: -3.5172
Max Act: 3.0459. Min Act: -0.1700
Data Index: 1576029 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19