Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2999 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2614. Min Range: -6.2614
Max Act: 6.2614. Min Act: -0.1700
Data Index: 8031928 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2614. Min Range: -6.2614
Max Act: 5.8239. Min Act: -0.1700
Data Index: 5311414 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2614. Min Range: -6.2614
Max Act: 5.7302. Min Act: -0.1700
Data Index: 712615 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2614. Min Range: -6.2614
Max Act: 5.6364. Min Act: -0.1700
Data Index: 6802830 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2614. Min Range: -6.2614
Max Act: 5.5739. Min Act: -0.1700
Data Index: 3444853 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2614. Min Range: -6.2614
Max Act: 5.5739. Min Act: -0.1700
Data Index: 3335398 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2614. Min Range: -6.2614
Max Act: 5.5427. Min Act: -0.1700
Data Index: 1394045 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2614. Min Range: -6.2614
Max Act: 5.5114. Min Act: -0.1700
Data Index: 1326033 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2614. Min Range: -6.2614
Max Act: 5.5114. Min Act: -0.1700
Data Index: 4829842 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2614. Min Range: -6.2614
Max Act: 5.4802. Min Act: -0.1700
Data Index: 5887988 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2614. Min Range: -6.2614
Max Act: 5.4489. Min Act: -0.1700
Data Index: 6669930 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2614. Min Range: -6.2614
Max Act: 5.4489. Min Act: -0.1700
Data Index: 4653297 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2614. Min Range: -6.2614
Max Act: 5.4489. Min Act: -0.1700
Data Index: 878363 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2614. Min Range: -6.2614
Max Act: 5.4489. Min Act: -0.1700
Data Index: 1895686 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2614. Min Range: -6.2614
Max Act: 5.4802. Min Act: -0.1700
Data Index: 762315 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2614. Min Range: -6.2614
Max Act: 5.4489. Min Act: -0.1700
Data Index: 992539 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2614. Min Range: -6.2614
Max Act: 5.4177. Min Act: -0.1700
Data Index: 8438685 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2614. Min Range: -6.2614
Max Act: 5.4177. Min Act: -0.1700
Data Index: 320101 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2614. Min Range: -6.2614
Max Act: 5.4177. Min Act: -0.1700
Data Index: 4866573 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2614. Min Range: -6.2614
Max Act: 5.3864. Min Act: -0.1700
Data Index: 7224156 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19