Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2981 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6184. Min Range: -8.6184
Max Act: 8.6184. Min Act: -0.1700
Data Index: 2667747 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6184. Min Range: -8.6184
Max Act: 8.2434. Min Act: -0.1700
Data Index: 4019617 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6184. Min Range: -8.6184
Max Act: 8.1809. Min Act: -0.1700
Data Index: 70791 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6184. Min Range: -8.6184
Max Act: 8.1809. Min Act: -0.1700
Data Index: 6391209 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6184. Min Range: -8.6184
Max Act: 8.1184. Min Act: -0.1700
Data Index: 555713 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6184. Min Range: -8.6184
Max Act: 8.1184. Min Act: -0.1700
Data Index: 3075549 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6184. Min Range: -8.6184
Max Act: 8.0559. Min Act: -0.1700
Data Index: 3252261 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6184. Min Range: -8.6184
Max Act: 8.0559. Min Act: -0.1700
Data Index: 2686467 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6184. Min Range: -8.6184
Max Act: 7.9934. Min Act: -0.1700
Data Index: 5805166 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6184. Min Range: -8.6184
Max Act: 7.9934. Min Act: -0.1700
Data Index: 428377 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6184. Min Range: -8.6184
Max Act: 7.9309. Min Act: -0.1700
Data Index: 7151623 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6184. Min Range: -8.6184
Max Act: 7.8684. Min Act: -0.1700
Data Index: 4449533 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6184. Min Range: -8.6184
Max Act: 7.8371. Min Act: -0.1700
Data Index: 767157 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6184. Min Range: -8.6184
Max Act: 7.8684. Min Act: -0.1700
Data Index: 5394577 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6184. Min Range: -8.6184
Max Act: 7.8371. Min Act: -0.1700
Data Index: 767156 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6184. Min Range: -8.6184
Max Act: 7.8684. Min Act: -0.1700
Data Index: 4054797 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6184. Min Range: -8.6184
Max Act: 7.8371. Min Act: -0.1700
Data Index: 5006595 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6184. Min Range: -8.6184
Max Act: 7.8371. Min Act: -0.1700
Data Index: 1022565 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6184. Min Range: -8.6184
Max Act: 7.8684. Min Act: -0.1700
Data Index: 2820649 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6184. Min Range: -8.6184
Max Act: 7.8059. Min Act: -0.1700
Data Index: 2304679 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19