Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3489 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5511. Min Range: -7.5511
Max Act: 7.5511. Min Act: -0.1700
Data Index: 7698730 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5511. Min Range: -7.5511
Max Act: 7.3948. Min Act: -0.1700
Data Index: 1357289 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5511. Min Range: -7.5511
Max Act: 7.3948. Min Act: -0.1700
Data Index: 2413134 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5511. Min Range: -7.5511
Max Act: 7.3323. Min Act: -0.1700
Data Index: 3759316 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5511. Min Range: -7.5511
Max Act: 7.3323. Min Act: -0.1700
Data Index: 7036363 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5511. Min Range: -7.5511
Max Act: 7.2698. Min Act: -0.1700
Data Index: 1771889 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5511. Min Range: -7.5511
Max Act: 7.2073. Min Act: -0.1700
Data Index: 5408964 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5511. Min Range: -7.5511
Max Act: 7.1761. Min Act: -0.1700
Data Index: 3152418 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5511. Min Range: -7.5511
Max Act: 7.1761. Min Act: -0.1700
Data Index: 1163559 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5511. Min Range: -7.5511
Max Act: 7.1448. Min Act: -0.1700
Data Index: 8585599 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5511. Min Range: -7.5511
Max Act: 7.1448. Min Act: -0.1700
Data Index: 1289128 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5511. Min Range: -7.5511
Max Act: 7.1448. Min Act: -0.1700
Data Index: 1101057 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5511. Min Range: -7.5511
Max Act: 7.1136. Min Act: -0.1700
Data Index: 1667789 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5511. Min Range: -7.5511
Max Act: 7.1136. Min Act: -0.1700
Data Index: 795915 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5511. Min Range: -7.5511
Max Act: 7.1136. Min Act: -0.1700
Data Index: 635488 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5511. Min Range: -7.5511
Max Act: 7.1448. Min Act: -0.1700
Data Index: 3534375 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5511. Min Range: -7.5511
Max Act: 7.1136. Min Act: -0.1700
Data Index: 7885876 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5511. Min Range: -7.5511
Max Act: 7.0823. Min Act: -0.1700
Data Index: 6937921 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5511. Min Range: -7.5511
Max Act: 7.0823. Min Act: -0.1700
Data Index: 6576233 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5511. Min Range: -7.5511
Max Act: 7.0823. Min Act: -0.1700
Data Index: 1709750 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19