Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1726 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7412. Min Range: -1.7412
Max Act: 1.7412. Min Act: -0.1700
Data Index: 7962413 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7412. Min Range: -1.7412
Max Act: 1.7326. Min Act: -0.1673
Data Index: 317554 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7412. Min Range: -1.7412
Max Act: 1.7152. Min Act: -0.1700
Data Index: 5288538 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7412. Min Range: -1.7412
Max Act: 1.7239. Min Act: -0.1700
Data Index: 4066426 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7412. Min Range: -1.7412
Max Act: 1.7066. Min Act: -0.1700
Data Index: 2145245 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7412. Min Range: -1.7412
Max Act: 1.7066. Min Act: -0.1699
Data Index: 4554504 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7412. Min Range: -1.7412
Max Act: 1.6979. Min Act: -0.1699
Data Index: 2867720 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7412. Min Range: -1.7412
Max Act: 1.6806. Min Act: -0.1700
Data Index: 3418321 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7412. Min Range: -1.7412
Max Act: 1.6719. Min Act: -0.1697
Data Index: 7581126 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7412. Min Range: -1.7412
Max Act: 1.6806. Min Act: -0.1542
Data Index: 7105656 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7412. Min Range: -1.7412
Max Act: 1.6632. Min Act: -0.1700
Data Index: 4390041 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7412. Min Range: -1.7412
Max Act: 1.6632. Min Act: -0.1700
Data Index: 8201993 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7412. Min Range: -1.7412
Max Act: 1.6632. Min Act: -0.1700
Data Index: 4048897 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7412. Min Range: -1.7412
Max Act: 1.6545. Min Act: -0.1699
Data Index: 5314140 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7412. Min Range: -1.7412
Max Act: 1.6719. Min Act: -0.1699
Data Index: 5017269 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7412. Min Range: -1.7412
Max Act: 1.6545. Min Act: -0.1700
Data Index: 3163970 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7412. Min Range: -1.7412
Max Act: 1.6806. Min Act: -0.1700
Data Index: 3339431 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7412. Min Range: -1.7412
Max Act: 1.6632. Min Act: -0.1700
Data Index: 4845381 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7412. Min Range: -1.7412
Max Act: 1.6545. Min Act: -0.1700
Data Index: 7581118 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7412. Min Range: -1.7412
Max Act: 1.6632. Min Act: -0.1669
Data Index: 5314130 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19