Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3175 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8560. Min Range: -3.8560
Max Act: 3.8560. Min Act: -0.1700
Data Index: 504050 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8560. Min Range: -3.8560
Max Act: 3.7622. Min Act: -0.1700
Data Index: 3209626 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8560. Min Range: -3.8560
Max Act: 3.6683. Min Act: -0.1700
Data Index: 8345651 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8560. Min Range: -3.8560
Max Act: 3.6370. Min Act: -0.1700
Data Index: 5598164 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8560. Min Range: -3.8560
Max Act: 3.6370. Min Act: -0.1700
Data Index: 8793254 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8560. Min Range: -3.8560
Max Act: 3.5744. Min Act: -0.1700
Data Index: 6372039 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8560. Min Range: -3.8560
Max Act: 3.5275. Min Act: -0.1700
Data Index: 8147974 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8560. Min Range: -3.8560
Max Act: 3.5275. Min Act: -0.1700
Data Index: 4886706 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8560. Min Range: -3.8560
Max Act: 3.4805. Min Act: -0.1700
Data Index: 2591760 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8560. Min Range: -3.8560
Max Act: 3.4805. Min Act: -0.1700
Data Index: 6865778 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8560. Min Range: -3.8560
Max Act: 3.4648. Min Act: -0.1700
Data Index: 185977 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8560. Min Range: -3.8560
Max Act: 3.4648. Min Act: -0.1700
Data Index: 1500540 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8560. Min Range: -3.8560
Max Act: 3.4648. Min Act: -0.1700
Data Index: 581081 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8560. Min Range: -3.8560
Max Act: 3.4805. Min Act: -0.1700
Data Index: 3927980 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8560. Min Range: -3.8560
Max Act: 3.4648. Min Act: -0.1700
Data Index: 6161595 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8560. Min Range: -3.8560
Max Act: 3.4805. Min Act: -0.1700
Data Index: 1624306 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8560. Min Range: -3.8560
Max Act: 3.4491. Min Act: -0.1700
Data Index: 1673653 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8560. Min Range: -3.8560
Max Act: 3.4491. Min Act: -0.1700
Data Index: 7223793 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8560. Min Range: -3.8560
Max Act: 3.4491. Min Act: -0.1700
Data Index: 844455 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8560. Min Range: -3.8560
Max Act: 3.4491. Min Act: -0.1700
Data Index: 250593 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19