Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1231 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3384. Min Range: -3.3384
Max Act: 3.3384. Min Act: -0.1700
Data Index: 7266282 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3384. Min Range: -3.3384
Max Act: 3.3070. Min Act: -0.1700
Data Index: 6858910 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3384. Min Range: -3.3384
Max Act: 3.2599. Min Act: -0.1700
Data Index: 4905163 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3384. Min Range: -3.3384
Max Act: 3.2442. Min Act: -0.1700
Data Index: 3610835 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3384. Min Range: -3.3384
Max Act: 3.2285. Min Act: -0.1700
Data Index: 2444862 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3384. Min Range: -3.3384
Max Act: 3.2285. Min Act: -0.1700
Data Index: 1192558 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3384. Min Range: -3.3384
Max Act: 3.1970. Min Act: -0.1700
Data Index: 1933051 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3384. Min Range: -3.3384
Max Act: 3.1813. Min Act: -0.1700
Data Index: 8288808 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3384. Min Range: -3.3384
Max Act: 3.1656. Min Act: -0.1700
Data Index: 3792493 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3384. Min Range: -3.3384
Max Act: 3.1656. Min Act: -0.1700
Data Index: 7169964 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3384. Min Range: -3.3384
Max Act: 3.1656. Min Act: -0.1700
Data Index: 8138962 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3384. Min Range: -3.3384
Max Act: 3.1341. Min Act: -0.1700
Data Index: 1765051 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3384. Min Range: -3.3384
Max Act: 3.1498. Min Act: -0.1700
Data Index: 1244500 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3384. Min Range: -3.3384
Max Act: 3.1498. Min Act: -0.1700
Data Index: 3384899 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3384. Min Range: -3.3384
Max Act: 3.1183. Min Act: -0.1700
Data Index: 4244231 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3384. Min Range: -3.3384
Max Act: 3.1341. Min Act: -0.1700
Data Index: 2123835 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3384. Min Range: -3.3384
Max Act: 3.1341. Min Act: -0.1700
Data Index: 1375023 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3384. Min Range: -3.3384
Max Act: 3.1341. Min Act: -0.1700
Data Index: 301884 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3384. Min Range: -3.3384
Max Act: 3.1341. Min Act: -0.1700
Data Index: 254434 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3384. Min Range: -3.3384
Max Act: 3.1341. Min Act: -0.1700
Data Index: 3590860 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19