Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 262 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.6210. Min Act: -0.1700
Data Index: 1374698 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.3085. Min Act: -0.1700
Data Index: 1593047 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.1522. Min Act: -0.1700
Data Index: 6474764 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.0585. Min Act: -0.1700
Data Index: 3613783 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.0585. Min Act: -0.1700
Data Index: 3213245 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.0585. Min Act: -0.1700
Data Index: 1467524 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.0272. Min Act: -0.1700
Data Index: 1292978 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.0272. Min Act: -0.1700
Data Index: 2198044 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6210. Min Range: -6.6210
Max Act: 5.9960. Min Act: -0.1700
Data Index: 3049535 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6210. Min Range: -6.6210
Max Act: 5.9647. Min Act: -0.1700
Data Index: 6731382 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6210. Min Range: -6.6210
Max Act: 5.9647. Min Act: -0.1700
Data Index: 6202106 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6210. Min Range: -6.6210
Max Act: 5.9335. Min Act: -0.1700
Data Index: 4048439 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6210. Min Range: -6.6210
Max Act: 5.9022. Min Act: -0.1700
Data Index: 5061729 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6210. Min Range: -6.6210
Max Act: 5.9022. Min Act: -0.1700
Data Index: 3893824 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6210. Min Range: -6.6210
Max Act: 5.8710. Min Act: -0.1700
Data Index: 4170776 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6210. Min Range: -6.6210
Max Act: 5.8710. Min Act: -0.1700
Data Index: 3517292 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6210. Min Range: -6.6210
Max Act: 5.9022. Min Act: -0.1700
Data Index: 6745069 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6210. Min Range: -6.6210
Max Act: 5.8710. Min Act: -0.1700
Data Index: 2976693 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6210. Min Range: -6.6210
Max Act: 5.8710. Min Act: -0.1700
Data Index: 3850240 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6210. Min Range: -6.6210
Max Act: 5.8397. Min Act: -0.1700
Data Index: 5522445 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19