Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 616 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9854. Min Range: -5.9854
Max Act: 5.9854. Min Act: -0.1700
Data Index: 4352738 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9854. Min Range: -5.9854
Max Act: 5.9229. Min Act: -0.1700
Data Index: 100308 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9854. Min Range: -5.9854
Max Act: 5.8916. Min Act: -0.1700
Data Index: 7511411 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9854. Min Range: -5.9854
Max Act: 5.8916. Min Act: -0.1700
Data Index: 535609 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9854. Min Range: -5.9854
Max Act: 5.8604. Min Act: -0.1700
Data Index: 7541910 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9854. Min Range: -5.9854
Max Act: 5.8604. Min Act: -0.1700
Data Index: 1191130 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9854. Min Range: -5.9854
Max Act: 5.8291. Min Act: -0.1700
Data Index: 452108 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9854. Min Range: -5.9854
Max Act: 5.7666. Min Act: -0.1700
Data Index: 3866305 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9854. Min Range: -5.9854
Max Act: 5.7666. Min Act: -0.1700
Data Index: 4020379 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9854. Min Range: -5.9854
Max Act: 5.7666. Min Act: -0.1700
Data Index: 1618192 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9854. Min Range: -5.9854
Max Act: 5.7041. Min Act: -0.1700
Data Index: 5262549 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9854. Min Range: -5.9854
Max Act: 5.7041. Min Act: -0.1700
Data Index: 7009605 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9854. Min Range: -5.9854
Max Act: 5.6729. Min Act: -0.1700
Data Index: 6495028 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9854. Min Range: -5.9854
Max Act: 5.6729. Min Act: -0.1700
Data Index: 6528598 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9854. Min Range: -5.9854
Max Act: 5.6416. Min Act: -0.1700
Data Index: 3754627 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9854. Min Range: -5.9854
Max Act: 5.6104. Min Act: -0.1700
Data Index: 54421 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9854. Min Range: -5.9854
Max Act: 5.6416. Min Act: -0.1700
Data Index: 1302524 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9854. Min Range: -5.9854
Max Act: 5.6104. Min Act: -0.1700
Data Index: 3769172 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9854. Min Range: -5.9854
Max Act: 5.6104. Min Act: -0.1700
Data Index: 7770060 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9854. Min Range: -5.9854
Max Act: 5.6104. Min Act: -0.1700
Data Index: 339827 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19