Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3208 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7111. Min Range: -7.7111
Max Act: 7.7111. Min Act: -0.1700
Data Index: 998397 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7111. Min Range: -7.7111
Max Act: 7.5861. Min Act: -0.1700
Data Index: 6135470 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7111. Min Range: -7.7111
Max Act: 7.4924. Min Act: -0.1700
Data Index: 2700336 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7111. Min Range: -7.7111
Max Act: 7.3986. Min Act: -0.1700
Data Index: 4183186 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7111. Min Range: -7.7111
Max Act: 7.3674. Min Act: -0.1700
Data Index: 2058999 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7111. Min Range: -7.7111
Max Act: 7.2736. Min Act: -0.1700
Data Index: 1046084 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7111. Min Range: -7.7111
Max Act: 7.2424. Min Act: -0.1700
Data Index: 8498449 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7111. Min Range: -7.7111
Max Act: 7.2424. Min Act: -0.1700
Data Index: 1331673 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7111. Min Range: -7.7111
Max Act: 7.2111. Min Act: -0.1700
Data Index: 3495093 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7111. Min Range: -7.7111
Max Act: 7.2111. Min Act: -0.1700
Data Index: 1574263 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7111. Min Range: -7.7111
Max Act: 7.1799. Min Act: -0.1700
Data Index: 715817 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7111. Min Range: -7.7111
Max Act: 7.1799. Min Act: -0.1700
Data Index: 5946897 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7111. Min Range: -7.7111
Max Act: 7.1799. Min Act: -0.1700
Data Index: 2609998 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7111. Min Range: -7.7111
Max Act: 7.1486. Min Act: -0.1700
Data Index: 762779 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7111. Min Range: -7.7111
Max Act: 7.1486. Min Act: -0.1700
Data Index: 2994962 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7111. Min Range: -7.7111
Max Act: 7.1486. Min Act: -0.1700
Data Index: 421547 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7111. Min Range: -7.7111
Max Act: 7.1174. Min Act: -0.1700
Data Index: 1793106 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7111. Min Range: -7.7111
Max Act: 7.0861. Min Act: -0.1700
Data Index: 4255523 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7111. Min Range: -7.7111
Max Act: 7.0861. Min Act: -0.1700
Data Index: 4929203 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7111. Min Range: -7.7111
Max Act: 7.0861. Min Act: -0.1700
Data Index: 6109628 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19