Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3998 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3073. Min Range: -6.3073
Max Act: 6.3073. Min Act: -0.1700
Data Index: 8511010 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3073. Min Range: -6.3073
Max Act: 6.2761. Min Act: -0.1700
Data Index: 5583225 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3073. Min Range: -6.3073
Max Act: 6.2136. Min Act: -0.1700
Data Index: 1148816 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3073. Min Range: -6.3073
Max Act: 6.2136. Min Act: -0.1700
Data Index: 5762845 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3073. Min Range: -6.3073
Max Act: 6.1823. Min Act: -0.1700
Data Index: 2501468 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3073. Min Range: -6.3073
Max Act: 6.1823. Min Act: -0.1700
Data Index: 4030288 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3073. Min Range: -6.3073
Max Act: 6.1511. Min Act: -0.1700
Data Index: 8509794 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3073. Min Range: -6.3073
Max Act: 6.1823. Min Act: -0.1700
Data Index: 8459154 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3073. Min Range: -6.3073
Max Act: 6.1511. Min Act: -0.1700
Data Index: 3935542 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3073. Min Range: -6.3073
Max Act: 6.1511. Min Act: -0.1700
Data Index: 370134 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3073. Min Range: -6.3073
Max Act: 6.1511. Min Act: -0.1700
Data Index: 5579170 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3073. Min Range: -6.3073
Max Act: 6.1198. Min Act: -0.1700
Data Index: 3763845 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3073. Min Range: -6.3073
Max Act: 6.1198. Min Act: -0.1700
Data Index: 1926438 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3073. Min Range: -6.3073
Max Act: 6.1198. Min Act: -0.1700
Data Index: 1510425 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3073. Min Range: -6.3073
Max Act: 6.1198. Min Act: -0.1700
Data Index: 3208495 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3073. Min Range: -6.3073
Max Act: 6.1198. Min Act: -0.1700
Data Index: 6483044 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3073. Min Range: -6.3073
Max Act: 6.1198. Min Act: -0.1700
Data Index: 1217966 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3073. Min Range: -6.3073
Max Act: 6.1198. Min Act: -0.1700
Data Index: 8555130 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3073. Min Range: -6.3073
Max Act: 6.0573. Min Act: -0.1700
Data Index: 8466337 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3073. Min Range: -6.3073
Max Act: 6.0886. Min Act: -0.1700
Data Index: 4850808 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19