Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5512 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1247. Min Range: -7.1247
Max Act: 7.1247. Min Act: -0.1700
Data Index: 4007689 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1247. Min Range: -7.1247
Max Act: 6.9997. Min Act: -0.1700
Data Index: 4844832 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1247. Min Range: -7.1247
Max Act: 6.8122. Min Act: -0.1700
Data Index: 5268807 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1247. Min Range: -7.1247
Max Act: 6.8122. Min Act: -0.1700
Data Index: 5622837 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1247. Min Range: -7.1247
Max Act: 6.6872. Min Act: -0.1700
Data Index: 8633966 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1247. Min Range: -7.1247
Max Act: 6.4685. Min Act: -0.1700
Data Index: 3522195 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1247. Min Range: -7.1247
Max Act: 6.4372. Min Act: -0.1700
Data Index: 7388581 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1247. Min Range: -7.1247
Max Act: 6.4372. Min Act: -0.1700
Data Index: 5174608 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1247. Min Range: -7.1247
Max Act: 6.4060. Min Act: -0.1700
Data Index: 7449421 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1247. Min Range: -7.1247
Max Act: 6.4060. Min Act: -0.1700
Data Index: 1079864 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1247. Min Range: -7.1247
Max Act: 6.3435. Min Act: -0.1700
Data Index: 7224551 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1247. Min Range: -7.1247
Max Act: 6.3122. Min Act: -0.1700
Data Index: 2601096 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1247. Min Range: -7.1247
Max Act: 6.3122. Min Act: -0.1700
Data Index: 6412192 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1247. Min Range: -7.1247
Max Act: 6.2810. Min Act: -0.1700
Data Index: 710832 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1247. Min Range: -7.1247
Max Act: 6.2810. Min Act: -0.1700
Data Index: 4130275 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1247. Min Range: -7.1247
Max Act: 6.2497. Min Act: -0.1700
Data Index: 170645 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1247. Min Range: -7.1247
Max Act: 6.2497. Min Act: -0.1700
Data Index: 1906743 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1247. Min Range: -7.1247
Max Act: 6.2497. Min Act: -0.1700
Data Index: 8215506 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1247. Min Range: -7.1247
Max Act: 6.2497. Min Act: -0.1700
Data Index: 4632398 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1247. Min Range: -7.1247
Max Act: 6.2185. Min Act: -0.1700
Data Index: 686163 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19