Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3026 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3691. Min Range: -5.3691
Max Act: 5.3691. Min Act: -0.1700
Data Index: 5040974 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3691. Min Range: -5.3691
Max Act: 5.3378. Min Act: -0.1700
Data Index: 1368467 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3691. Min Range: -5.3691
Max Act: 5.3378. Min Act: -0.1700
Data Index: 835346 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3691. Min Range: -5.3691
Max Act: 5.2753. Min Act: -0.1700
Data Index: 5708347 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3691. Min Range: -5.3691
Max Act: 5.2753. Min Act: -0.1700
Data Index: 1928152 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3691. Min Range: -5.3691
Max Act: 5.2441. Min Act: -0.1700
Data Index: 2888053 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3691. Min Range: -5.3691
Max Act: 5.2441. Min Act: -0.1700
Data Index: 2535434 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3691. Min Range: -5.3691
Max Act: 5.2441. Min Act: -0.1700
Data Index: 8832026 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3691. Min Range: -5.3691
Max Act: 5.2441. Min Act: -0.1700
Data Index: 6164711 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3691. Min Range: -5.3691
Max Act: 5.2128. Min Act: -0.1700
Data Index: 5533006 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3691. Min Range: -5.3691
Max Act: 5.2128. Min Act: -0.1700
Data Index: 899475 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3691. Min Range: -5.3691
Max Act: 5.1816. Min Act: -0.1700
Data Index: 2123492 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3691. Min Range: -5.3691
Max Act: 5.2128. Min Act: -0.1700
Data Index: 7961633 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3691. Min Range: -5.3691
Max Act: 5.2128. Min Act: -0.1700
Data Index: 6009458 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3691. Min Range: -5.3691
Max Act: 5.1816. Min Act: -0.1700
Data Index: 7453378 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3691. Min Range: -5.3691
Max Act: 5.2128. Min Act: -0.1700
Data Index: 5731223 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3691. Min Range: -5.3691
Max Act: 5.2128. Min Act: -0.1700
Data Index: 531916 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3691. Min Range: -5.3691
Max Act: 5.2128. Min Act: -0.1700
Data Index: 906016 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3691. Min Range: -5.3691
Max Act: 5.1816. Min Act: -0.1700
Data Index: 2845952 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3691. Min Range: -5.3691
Max Act: 5.2128. Min Act: -0.1700
Data Index: 5158017 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19