Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3602 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0102. Min Range: -8.0102
Max Act: 8.0102. Min Act: -0.1700
Data Index: 1955786 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0102. Min Range: -8.0102
Max Act: 7.7289. Min Act: -0.1700
Data Index: 5844748 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0102. Min Range: -8.0102
Max Act: 7.6352. Min Act: -0.1700
Data Index: 1399706 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0102. Min Range: -8.0102
Max Act: 7.6664. Min Act: -0.1700
Data Index: 2980557 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0102. Min Range: -8.0102
Max Act: 7.4789. Min Act: -0.1700
Data Index: 2464767 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0102. Min Range: -8.0102
Max Act: 7.4477. Min Act: -0.1700
Data Index: 8086508 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0102. Min Range: -8.0102
Max Act: 7.4789. Min Act: -0.1700
Data Index: 2035667 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0102. Min Range: -8.0102
Max Act: 7.4477. Min Act: -0.1700
Data Index: 2464770 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0102. Min Range: -8.0102
Max Act: 7.4477. Min Act: -0.1700
Data Index: 6743594 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0102. Min Range: -8.0102
Max Act: 7.3852. Min Act: -0.1700
Data Index: 4054146 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0102. Min Range: -8.0102
Max Act: 7.4164. Min Act: -0.1700
Data Index: 1559395 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0102. Min Range: -8.0102
Max Act: 7.4164. Min Act: -0.1700
Data Index: 694861 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0102. Min Range: -8.0102
Max Act: 7.3539. Min Act: -0.1700
Data Index: 3905365 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0102. Min Range: -8.0102
Max Act: 7.3852. Min Act: -0.1700
Data Index: 3912410 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0102. Min Range: -8.0102
Max Act: 7.3539. Min Act: -0.1700
Data Index: 4006228 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0102. Min Range: -8.0102
Max Act: 7.2914. Min Act: -0.1700
Data Index: 373220 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0102. Min Range: -8.0102
Max Act: 7.2914. Min Act: -0.1699
Data Index: 4116367 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0102. Min Range: -8.0102
Max Act: 7.3227. Min Act: -0.1700
Data Index: 785508 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0102. Min Range: -8.0102
Max Act: 7.3227. Min Act: -0.1700
Data Index: 6139708 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0102. Min Range: -8.0102
Max Act: 7.3227. Min Act: -0.1700
Data Index: 5840347 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19