Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3256 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4818. Min Range: -3.4818
Max Act: 3.4818. Min Act: -0.1700
Data Index: 4253078 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4818. Min Range: -3.4818
Max Act: 3.3407. Min Act: -0.1700
Data Index: 5894147 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4818. Min Range: -3.4818
Max Act: 3.2465. Min Act: -0.1700
Data Index: 940783 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4818. Min Range: -3.4818
Max Act: 3.1993. Min Act: -0.1700
Data Index: 4856449 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4818. Min Range: -3.4818
Max Act: 3.1679. Min Act: -0.1700
Data Index: 131033 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4818. Min Range: -3.4818
Max Act: 3.1521. Min Act: -0.1700
Data Index: 2311010 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4818. Min Range: -3.4818
Max Act: 3.1364. Min Act: -0.1700
Data Index: 4507383 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4818. Min Range: -3.4818
Max Act: 3.1049. Min Act: -0.1700
Data Index: 74221 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4818. Min Range: -3.4818
Max Act: 3.1206. Min Act: -0.1700
Data Index: 2242294 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4818. Min Range: -3.4818
Max Act: 3.0891. Min Act: -0.1700
Data Index: 80090 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4818. Min Range: -3.4818
Max Act: 3.0576. Min Act: -0.1700
Data Index: 2040956 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4818. Min Range: -3.4818
Max Act: 3.0576. Min Act: -0.1700
Data Index: 535601 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4818. Min Range: -3.4818
Max Act: 3.0418. Min Act: -0.1700
Data Index: 1890545 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4818. Min Range: -3.4818
Max Act: 3.0260. Min Act: -0.1700
Data Index: 3061581 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4818. Min Range: -3.4818
Max Act: 3.0260. Min Act: -0.1700
Data Index: 7321921 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4818. Min Range: -3.4818
Max Act: 3.0260. Min Act: -0.1700
Data Index: 8400945 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4818. Min Range: -3.4818
Max Act: 3.0260. Min Act: -0.1700
Data Index: 663435 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4818. Min Range: -3.4818
Max Act: 3.0102. Min Act: -0.1700
Data Index: 7281281 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4818. Min Range: -3.4818
Max Act: 3.0102. Min Act: -0.1700
Data Index: 5959992 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4818. Min Range: -3.4818
Max Act: 3.0102. Min Act: -0.1700
Data Index: 1095270 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19