Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 343 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5802. Min Range: -8.5802
Max Act: 8.5802. Min Act: -0.1700
Data Index: 7175972 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5802. Min Range: -8.5802
Max Act: 8.1427. Min Act: -0.1700
Data Index: 2078701 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5802. Min Range: -8.5802
Max Act: 8.0177. Min Act: -0.1700
Data Index: 2084807 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5802. Min Range: -8.5802
Max Act: 7.7677. Min Act: -0.1700
Data Index: 8416882 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5802. Min Range: -8.5802
Max Act: 7.7677. Min Act: -0.1700
Data Index: 1571062 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5802. Min Range: -8.5802
Max Act: 7.7677. Min Act: -0.1700
Data Index: 2119405 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5802. Min Range: -8.5802
Max Act: 7.7365. Min Act: -0.1700
Data Index: 214826 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5802. Min Range: -8.5802
Max Act: 7.7365. Min Act: -0.1700
Data Index: 7333507 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5802. Min Range: -8.5802
Max Act: 7.6427. Min Act: -0.1700
Data Index: 5636015 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5802. Min Range: -8.5802
Max Act: 7.6427. Min Act: -0.1700
Data Index: 7200329 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5802. Min Range: -8.5802
Max Act: 7.6115. Min Act: -0.1700
Data Index: 3471450 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5802. Min Range: -8.5802
Max Act: 7.5802. Min Act: -0.1700
Data Index: 794461 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5802. Min Range: -8.5802
Max Act: 7.5802. Min Act: -0.1700
Data Index: 2739470 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5802. Min Range: -8.5802
Max Act: 7.5177. Min Act: -0.1700
Data Index: 2189027 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5802. Min Range: -8.5802
Max Act: 7.5177. Min Act: -0.1700
Data Index: 2836966 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5802. Min Range: -8.5802
Max Act: 7.5177. Min Act: -0.1700
Data Index: 1940082 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5802. Min Range: -8.5802
Max Act: 7.5177. Min Act: -0.1700
Data Index: 7318136 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5802. Min Range: -8.5802
Max Act: 7.5177. Min Act: -0.1700
Data Index: 2581365 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5802. Min Range: -8.5802
Max Act: 7.4865. Min Act: -0.1700
Data Index: 905767 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5802. Min Range: -8.5802
Max Act: 7.4865. Min Act: -0.1700
Data Index: 7144800 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19