Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4548 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3407. Min Range: -9.3407
Max Act: 9.3407. Min Act: -0.1700
Data Index: 4968111 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3407. Min Range: -9.3407
Max Act: 8.4032. Min Act: -0.1700
Data Index: 4589028 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3407. Min Range: -9.3407
Max Act: 8.3407. Min Act: -0.1700
Data Index: 1204063 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3407. Min Range: -9.3407
Max Act: 8.2782. Min Act: -0.1700
Data Index: 7660951 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3407. Min Range: -9.3407
Max Act: 8.1532. Min Act: -0.1700
Data Index: 5673611 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3407. Min Range: -9.3407
Max Act: 8.2157. Min Act: -0.1700
Data Index: 2002973 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3407. Min Range: -9.3407
Max Act: 8.1532. Min Act: -0.1700
Data Index: 4235943 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3407. Min Range: -9.3407
Max Act: 8.1532. Min Act: -0.1700
Data Index: 8291427 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3407. Min Range: -9.3407
Max Act: 8.0907. Min Act: -0.1700
Data Index: 4584179 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3407. Min Range: -9.3407
Max Act: 8.0907. Min Act: -0.1700
Data Index: 1678411 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3407. Min Range: -9.3407
Max Act: 8.0907. Min Act: -0.1700
Data Index: 5287700 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3407. Min Range: -9.3407
Max Act: 8.0282. Min Act: -0.1700
Data Index: 3283987 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3407. Min Range: -9.3407
Max Act: 8.0907. Min Act: -0.1700
Data Index: 4972893 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3407. Min Range: -9.3407
Max Act: 8.0907. Min Act: -0.1700
Data Index: 7188857 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3407. Min Range: -9.3407
Max Act: 8.0907. Min Act: -0.1700
Data Index: 4379160 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3407. Min Range: -9.3407
Max Act: 8.0282. Min Act: -0.1700
Data Index: 7506050 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3407. Min Range: -9.3407
Max Act: 8.0282. Min Act: -0.1700
Data Index: 7886148 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3407. Min Range: -9.3407
Max Act: 7.9657. Min Act: -0.1700
Data Index: 4602431 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3407. Min Range: -9.3407
Max Act: 7.9657. Min Act: -0.1700
Data Index: 2120749 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3407. Min Range: -9.3407
Max Act: 7.9032. Min Act: -0.1700
Data Index: 3993639 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19