Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3916 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0101. Min Range: -7.0101
Max Act: 7.0101. Min Act: -0.1700
Data Index: 1025437 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0101. Min Range: -7.0101
Max Act: 6.6351. Min Act: -0.1700
Data Index: 4862463 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0101. Min Range: -7.0101
Max Act: 6.5726. Min Act: -0.1700
Data Index: 515989 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0101. Min Range: -7.0101
Max Act: 6.5101. Min Act: -0.1700
Data Index: 1012793 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0101. Min Range: -7.0101
Max Act: 6.5101. Min Act: -0.1700
Data Index: 8593555 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0101. Min Range: -7.0101
Max Act: 6.4789. Min Act: -0.1700
Data Index: 8201348 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0101. Min Range: -7.0101
Max Act: 6.4164. Min Act: -0.1700
Data Index: 49124 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0101. Min Range: -7.0101
Max Act: 6.3851. Min Act: -0.1700
Data Index: 6491625 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0101. Min Range: -7.0101
Max Act: 6.3539. Min Act: -0.1700
Data Index: 7870378 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0101. Min Range: -7.0101
Max Act: 6.3539. Min Act: -0.1700
Data Index: 1187512 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0101. Min Range: -7.0101
Max Act: 6.2914. Min Act: -0.1700
Data Index: 2222750 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0101. Min Range: -7.0101
Max Act: 6.2289. Min Act: -0.1700
Data Index: 2177498 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0101. Min Range: -7.0101
Max Act: 6.2601. Min Act: -0.1700
Data Index: 493514 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0101. Min Range: -7.0101
Max Act: 6.2601. Min Act: -0.1700
Data Index: 96175 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0101. Min Range: -7.0101
Max Act: 6.2289. Min Act: -0.1700
Data Index: 4372463 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0101. Min Range: -7.0101
Max Act: 6.2289. Min Act: -0.1700
Data Index: 2872195 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0101. Min Range: -7.0101
Max Act: 6.2289. Min Act: -0.1700
Data Index: 158592 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0101. Min Range: -7.0101
Max Act: 6.2289. Min Act: -0.1700
Data Index: 5019066 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0101. Min Range: -7.0101
Max Act: 6.1976. Min Act: -0.1700
Data Index: 8416493 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0101. Min Range: -7.0101
Max Act: 6.1664. Min Act: -0.1700
Data Index: 6643114 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19