Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3986 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0229. Min Range: -7.0229
Max Act: 7.0229. Min Act: -0.1700
Data Index: 5168394 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0229. Min Range: -7.0229
Max Act: 6.8041. Min Act: -0.1700
Data Index: 975894 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0229. Min Range: -7.0229
Max Act: 6.7729. Min Act: -0.1700
Data Index: 7958180 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0229. Min Range: -7.0229
Max Act: 6.7729. Min Act: -0.1700
Data Index: 2361462 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0229. Min Range: -7.0229
Max Act: 6.7416. Min Act: -0.1700
Data Index: 4078317 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0229. Min Range: -7.0229
Max Act: 6.7104. Min Act: -0.1700
Data Index: 4373226 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0229. Min Range: -7.0229
Max Act: 6.7104. Min Act: -0.1700
Data Index: 3218000 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0229. Min Range: -7.0229
Max Act: 6.6479. Min Act: -0.1700
Data Index: 1988928 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0229. Min Range: -7.0229
Max Act: 6.6791. Min Act: -0.1700
Data Index: 6875393 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0229. Min Range: -7.0229
Max Act: 6.7104. Min Act: -0.1700
Data Index: 3124703 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0229. Min Range: -7.0229
Max Act: 6.6479. Min Act: -0.1700
Data Index: 205976 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0229. Min Range: -7.0229
Max Act: 6.6791. Min Act: -0.1700
Data Index: 2845973 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0229. Min Range: -7.0229
Max Act: 6.6479. Min Act: -0.1700
Data Index: 963678 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0229. Min Range: -7.0229
Max Act: 6.6479. Min Act: -0.1700
Data Index: 1379801 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0229. Min Range: -7.0229
Max Act: 6.6166. Min Act: -0.1700
Data Index: 1335601 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0229. Min Range: -7.0229
Max Act: 6.6166. Min Act: -0.1700
Data Index: 4368768 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0229. Min Range: -7.0229
Max Act: 6.6166. Min Act: -0.1700
Data Index: 8086079 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0229. Min Range: -7.0229
Max Act: 6.5541. Min Act: -0.1700
Data Index: 8788181 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0229. Min Range: -7.0229
Max Act: 6.5541. Min Act: -0.1700
Data Index: 3533403 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0229. Min Range: -7.0229
Max Act: 6.5541. Min Act: -0.1700
Data Index: 7846238 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19