Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2914 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2614. Min Range: -7.2614
Max Act: 7.2614. Min Act: -0.1700
Data Index: 2445244 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2614. Min Range: -7.2614
Max Act: 6.9802. Min Act: -0.1700
Data Index: 2387007 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2614. Min Range: -7.2614
Max Act: 6.8239. Min Act: -0.1700
Data Index: 2316401 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2614. Min Range: -7.2614
Max Act: 6.8552. Min Act: -0.1700
Data Index: 568049 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2614. Min Range: -7.2614
Max Act: 6.8239. Min Act: -0.1700
Data Index: 6769593 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2614. Min Range: -7.2614
Max Act: 6.7302. Min Act: -0.1700
Data Index: 6608454 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2614. Min Range: -7.2614
Max Act: 6.7302. Min Act: -0.1700
Data Index: 6769591 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2614. Min Range: -7.2614
Max Act: 6.6989. Min Act: -0.1700
Data Index: 2254460 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2614. Min Range: -7.2614
Max Act: 6.6989. Min Act: -0.1700
Data Index: 7061567 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2614. Min Range: -7.2614
Max Act: 6.6989. Min Act: -0.1700
Data Index: 875529 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2614. Min Range: -7.2614
Max Act: 6.6677. Min Act: -0.1700
Data Index: 1263128 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2614. Min Range: -7.2614
Max Act: 6.6677. Min Act: -0.1700
Data Index: 30687 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2614. Min Range: -7.2614
Max Act: 6.6677. Min Act: -0.1700
Data Index: 3523454 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2614. Min Range: -7.2614
Max Act: 6.6677. Min Act: -0.1700
Data Index: 7122550 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2614. Min Range: -7.2614
Max Act: 6.6364. Min Act: -0.1700
Data Index: 8723931 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2614. Min Range: -7.2614
Max Act: 6.6364. Min Act: -0.1700
Data Index: 2443415 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2614. Min Range: -7.2614
Max Act: 6.6364. Min Act: -0.1700
Data Index: 4745068 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2614. Min Range: -7.2614
Max Act: 6.6364. Min Act: -0.1700
Data Index: 6173499 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2614. Min Range: -7.2614
Max Act: 6.6052. Min Act: -0.1700
Data Index: 4597040 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2614. Min Range: -7.2614
Max Act: 6.6052. Min Act: -0.1700
Data Index: 307765 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19