Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5783 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2219. Min Range: -6.2219
Max Act: 6.2219. Min Act: -0.1700
Data Index: 7436490 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2219. Min Range: -6.2219
Max Act: 6.0344. Min Act: -0.1700
Data Index: 6221281 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2219. Min Range: -6.2219
Max Act: 6.0656. Min Act: -0.1700
Data Index: 7998357 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2219. Min Range: -6.2219
Max Act: 5.9406. Min Act: -0.1700
Data Index: 6716086 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2219. Min Range: -6.2219
Max Act: 5.7531. Min Act: -0.1700
Data Index: 8564835 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2219. Min Range: -6.2219
Max Act: 5.7219. Min Act: -0.1700
Data Index: 2488509 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2219. Min Range: -6.2219
Max Act: 5.6594. Min Act: -0.1700
Data Index: 1075001 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2219. Min Range: -6.2219
Max Act: 5.6281. Min Act: -0.1700
Data Index: 6379317 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2219. Min Range: -6.2219
Max Act: 5.6281. Min Act: -0.1700
Data Index: 6657442 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2219. Min Range: -6.2219
Max Act: 5.5969. Min Act: -0.1700
Data Index: 4216928 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2219. Min Range: -6.2219
Max Act: 5.6281. Min Act: -0.1700
Data Index: 6908217 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2219. Min Range: -6.2219
Max Act: 5.5656. Min Act: -0.1700
Data Index: 2826861 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2219. Min Range: -6.2219
Max Act: 5.5656. Min Act: -0.1700
Data Index: 6844239 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2219. Min Range: -6.2219
Max Act: 5.5969. Min Act: -0.1700
Data Index: 6427030 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2219. Min Range: -6.2219
Max Act: 5.5344. Min Act: -0.1700
Data Index: 1857791 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2219. Min Range: -6.2219
Max Act: 5.5344. Min Act: -0.1700
Data Index: 3748010 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2219. Min Range: -6.2219
Max Act: 5.5344. Min Act: -0.1700
Data Index: 4748498 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2219. Min Range: -6.2219
Max Act: 5.5031. Min Act: -0.1700
Data Index: 202792 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2219. Min Range: -6.2219
Max Act: 5.5031. Min Act: -0.1700
Data Index: 5137614 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2219. Min Range: -6.2219
Max Act: 5.4719. Min Act: -0.1700
Data Index: 3691820 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19