Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3166 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8282. Min Range: -7.8282
Max Act: 7.8282. Min Act: -0.1700
Data Index: 2615998 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8282. Min Range: -7.8282
Max Act: 7.6407. Min Act: -0.1700
Data Index: 1636298 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8282. Min Range: -7.8282
Max Act: 7.1407. Min Act: -0.1700
Data Index: 6285343 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8282. Min Range: -7.8282
Max Act: 7.1720. Min Act: -0.1700
Data Index: 7530769 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8282. Min Range: -7.8282
Max Act: 7.1095. Min Act: -0.1700
Data Index: 2719593 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8282. Min Range: -7.8282
Max Act: 7.0782. Min Act: -0.1700
Data Index: 2592254 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8282. Min Range: -7.8282
Max Act: 7.0157. Min Act: -0.1700
Data Index: 1212039 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8282. Min Range: -7.8282
Max Act: 7.0157. Min Act: -0.1700
Data Index: 8513797 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8282. Min Range: -7.8282
Max Act: 7.0157. Min Act: -0.1700
Data Index: 7428699 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8282. Min Range: -7.8282
Max Act: 6.9845. Min Act: -0.1700
Data Index: 8301266 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8282. Min Range: -7.8282
Max Act: 6.9532. Min Act: -0.1700
Data Index: 8487182 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8282. Min Range: -7.8282
Max Act: 6.9220. Min Act: -0.1700
Data Index: 201398 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8282. Min Range: -7.8282
Max Act: 6.9220. Min Act: -0.1700
Data Index: 2307190 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8282. Min Range: -7.8282
Max Act: 6.8907. Min Act: -0.1700
Data Index: 5665399 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8282. Min Range: -7.8282
Max Act: 6.8907. Min Act: -0.1700
Data Index: 2883431 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8282. Min Range: -7.8282
Max Act: 6.8907. Min Act: -0.1700
Data Index: 7009535 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8282. Min Range: -7.8282
Max Act: 6.8595. Min Act: -0.1700
Data Index: 2926358 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8282. Min Range: -7.8282
Max Act: 6.8907. Min Act: -0.1700
Data Index: 5448671 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8282. Min Range: -7.8282
Max Act: 6.8595. Min Act: -0.1700
Data Index: 48703 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8282. Min Range: -7.8282
Max Act: 6.8595. Min Act: -0.1700
Data Index: 3098646 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19