Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2744 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1421. Min Range: -8.1421
Max Act: 8.1421. Min Act: -0.1700
Data Index: 3209594 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1421. Min Range: -8.1421
Max Act: 8.1421. Min Act: -0.1700
Data Index: 3209595 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1421. Min Range: -8.1421
Max Act: 7.9546. Min Act: -0.1700
Data Index: 5417516 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1421. Min Range: -8.1421
Max Act: 7.8296. Min Act: -0.1700
Data Index: 4626861 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1421. Min Range: -8.1421
Max Act: 7.7984. Min Act: -0.1700
Data Index: 3480925 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1421. Min Range: -8.1421
Max Act: 7.7359. Min Act: -0.1700
Data Index: 2151487 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1421. Min Range: -8.1421
Max Act: 7.6734. Min Act: -0.1700
Data Index: 7831271 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1421. Min Range: -8.1421
Max Act: 7.7359. Min Act: -0.1700
Data Index: 1248736 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1421. Min Range: -8.1421
Max Act: 7.6421. Min Act: -0.1700
Data Index: 36180 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1421. Min Range: -8.1421
Max Act: 7.6109. Min Act: -0.1700
Data Index: 2669215 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1421. Min Range: -8.1421
Max Act: 7.6109. Min Act: -0.1700
Data Index: 8533688 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1421. Min Range: -8.1421
Max Act: 7.5484. Min Act: -0.1700
Data Index: 3631587 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1421. Min Range: -8.1421
Max Act: 7.5171. Min Act: -0.1700
Data Index: 6086962 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1421. Min Range: -8.1421
Max Act: 7.4859. Min Act: -0.1700
Data Index: 7666581 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1421. Min Range: -8.1421
Max Act: 7.5171. Min Act: -0.1700
Data Index: 6114582 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1421. Min Range: -8.1421
Max Act: 7.5171. Min Act: -0.1700
Data Index: 1311676 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1421. Min Range: -8.1421
Max Act: 7.4859. Min Act: -0.1700
Data Index: 5695477 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1421. Min Range: -8.1421
Max Act: 7.4859. Min Act: -0.1700
Data Index: 1653307 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1421. Min Range: -8.1421
Max Act: 7.4546. Min Act: -0.1700
Data Index: 4501046 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1421. Min Range: -8.1421
Max Act: 7.4859. Min Act: -0.1700
Data Index: 3121199 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19