Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3667 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3217. Min Range: -6.3217
Max Act: 6.3217. Min Act: -0.1700
Data Index: 1287402 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3217. Min Range: -6.3217
Max Act: 6.0404. Min Act: -0.1700
Data Index: 2104226 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3217. Min Range: -6.3217
Max Act: 6.0404. Min Act: -0.1700
Data Index: 480241 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3217. Min Range: -6.3217
Max Act: 6.0404. Min Act: -0.1700
Data Index: 844722 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3217. Min Range: -6.3217
Max Act: 5.9154. Min Act: -0.1700
Data Index: 3043345 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3217. Min Range: -6.3217
Max Act: 5.8842. Min Act: -0.1693
Data Index: 2104223 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3217. Min Range: -6.3217
Max Act: 5.8529. Min Act: -0.1700
Data Index: 3717846 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3217. Min Range: -6.3217
Max Act: 5.8529. Min Act: -0.1700
Data Index: 20376 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3217. Min Range: -6.3217
Max Act: 5.8529. Min Act: -0.1700
Data Index: 1727897 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3217. Min Range: -6.3217
Max Act: 5.8217. Min Act: -0.1700
Data Index: 1644525 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3217. Min Range: -6.3217
Max Act: 5.7904. Min Act: -0.1700
Data Index: 1727898 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3217. Min Range: -6.3217
Max Act: 5.7592. Min Act: -0.1700
Data Index: 6777570 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3217. Min Range: -6.3217
Max Act: 5.7592. Min Act: -0.1700
Data Index: 8147612 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3217. Min Range: -6.3217
Max Act: 5.7279. Min Act: -0.1697
Data Index: 1724454 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3217. Min Range: -6.3217
Max Act: 5.7279. Min Act: -0.1700
Data Index: 289801 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3217. Min Range: -6.3217
Max Act: 5.7279. Min Act: -0.1700
Data Index: 235323 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3217. Min Range: -6.3217
Max Act: 5.7279. Min Act: -0.1687
Data Index: 4748601 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3217. Min Range: -6.3217
Max Act: 5.7279. Min Act: -0.1700
Data Index: 2328938 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3217. Min Range: -6.3217
Max Act: 5.7279. Min Act: -0.1700
Data Index: 1662819 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3217. Min Range: -6.3217
Max Act: 5.7279. Min Act: -0.1698
Data Index: 6928270 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19