Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2749 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.9423. Min Act: -0.1700
Data Index: 1178603 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.9110. Min Act: -0.1700
Data Index: 6191256 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.8798. Min Act: -0.1700
Data Index: 7467931 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.9110. Min Act: -0.1700
Data Index: 7662591 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.8485. Min Act: -0.1700
Data Index: 4506978 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.8485. Min Act: -0.1700
Data Index: 6357980 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.8485. Min Act: -0.1700
Data Index: 2504428 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.8173. Min Act: -0.1700
Data Index: 1250189 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.8173. Min Act: -0.1700
Data Index: 6516096 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.8173. Min Act: -0.1700
Data Index: 2567028 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.7860. Min Act: -0.1700
Data Index: 3328969 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.7548. Min Act: -0.1700
Data Index: 4130706 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.7860. Min Act: -0.1700
Data Index: 682863 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.7860. Min Act: -0.1700
Data Index: 542669 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.7860. Min Act: -0.1700
Data Index: 8294973 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.7860. Min Act: -0.1700
Data Index: 5826526 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.7548. Min Act: -0.1700
Data Index: 3834967 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.7235. Min Act: -0.1700
Data Index: 3170834 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.7548. Min Act: -0.1700
Data Index: 2257278 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.7548. Min Act: -0.1699
Data Index: 4135146 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19