Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1585 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6435. Min Range: -5.6435
Max Act: 5.6435. Min Act: -0.1700
Data Index: 5599034 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6435. Min Range: -5.6435
Max Act: 5.5497. Min Act: -0.1700
Data Index: 8338287 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6435. Min Range: -5.6435
Max Act: 5.4872. Min Act: -0.1700
Data Index: 5917161 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6435. Min Range: -5.6435
Max Act: 5.4247. Min Act: -0.1700
Data Index: 7530176 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6435. Min Range: -5.6435
Max Act: 5.4247. Min Act: -0.1700
Data Index: 5047414 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6435. Min Range: -5.6435
Max Act: 5.4560. Min Act: -0.1700
Data Index: 5599033 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6435. Min Range: -5.6435
Max Act: 5.3935. Min Act: -0.1700
Data Index: 5152743 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6435. Min Range: -5.6435
Max Act: 5.4247. Min Act: -0.1700
Data Index: 7441177 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6435. Min Range: -5.6435
Max Act: 5.3935. Min Act: -0.1700
Data Index: 5099566 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6435. Min Range: -5.6435
Max Act: 5.3935. Min Act: -0.1700
Data Index: 2166195 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6435. Min Range: -5.6435
Max Act: 5.3622. Min Act: -0.1700
Data Index: 1710020 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6435. Min Range: -5.6435
Max Act: 5.3622. Min Act: -0.1700
Data Index: 462743 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6435. Min Range: -5.6435
Max Act: 5.3622. Min Act: -0.1700
Data Index: 688466 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6435. Min Range: -5.6435
Max Act: 5.3310. Min Act: -0.1700
Data Index: 1216050 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6435. Min Range: -5.6435
Max Act: 5.3310. Min Act: -0.1700
Data Index: 8735999 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6435. Min Range: -5.6435
Max Act: 5.3310. Min Act: -0.1700
Data Index: 1250088 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6435. Min Range: -5.6435
Max Act: 5.2997. Min Act: -0.1700
Data Index: 186651 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6435. Min Range: -5.6435
Max Act: 5.2997. Min Act: -0.1700
Data Index: 8509747 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6435. Min Range: -5.6435
Max Act: 5.2997. Min Act: -0.1700
Data Index: 392661 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6435. Min Range: -5.6435
Max Act: 5.2997. Min Act: -0.1700
Data Index: 3855310 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19