Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3140 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2220. Min Range: -4.2220
Max Act: 4.2220. Min Act: -0.1700
Data Index: 1735736 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2220. Min Range: -4.2220
Max Act: 4.2220. Min Act: -0.1700
Data Index: 3704539 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2220. Min Range: -4.2220
Max Act: 4.1908. Min Act: -0.1700
Data Index: 1642864 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2220. Min Range: -4.2220
Max Act: 4.1595. Min Act: -0.1700
Data Index: 7489619 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2220. Min Range: -4.2220
Max Act: 4.0970. Min Act: -0.1700
Data Index: 8827711 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2220. Min Range: -4.2220
Max Act: 4.0970. Min Act: -0.1700
Data Index: 4412987 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2220. Min Range: -4.2220
Max Act: 4.0658. Min Act: -0.1700
Data Index: 4300188 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2220. Min Range: -4.2220
Max Act: 4.0658. Min Act: -0.1700
Data Index: 3676698 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2220. Min Range: -4.2220
Max Act: 4.0658. Min Act: -0.1700
Data Index: 912913 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2220. Min Range: -4.2220
Max Act: 4.0658. Min Act: -0.1700
Data Index: 3803544 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2220. Min Range: -4.2220
Max Act: 4.0033. Min Act: -0.1700
Data Index: 4802903 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2220. Min Range: -4.2220
Max Act: 4.0345. Min Act: -0.1700
Data Index: 4588296 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2220. Min Range: -4.2220
Max Act: 4.0345. Min Act: -0.1700
Data Index: 2878294 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2220. Min Range: -4.2220
Max Act: 4.0345. Min Act: -0.1700
Data Index: 8296945 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2220. Min Range: -4.2220
Max Act: 4.0345. Min Act: -0.1700
Data Index: 5427036 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2220. Min Range: -4.2220
Max Act: 4.0345. Min Act: -0.1700
Data Index: 7499696 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2220. Min Range: -4.2220
Max Act: 4.0345. Min Act: -0.1700
Data Index: 7380979 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2220. Min Range: -4.2220
Max Act: 4.0345. Min Act: -0.1700
Data Index: 5626821 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2220. Min Range: -4.2220
Max Act: 4.0345. Min Act: -0.1700
Data Index: 1328131 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2220. Min Range: -4.2220
Max Act: 4.0033. Min Act: -0.1700
Data Index: 586144 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19