Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3806 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8196. Min Range: -6.8196
Max Act: 6.8196. Min Act: -0.1700
Data Index: 1962406 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8196. Min Range: -6.8196
Max Act: 6.6321. Min Act: -0.1700
Data Index: 4959134 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8196. Min Range: -6.8196
Max Act: 6.6008. Min Act: -0.1700
Data Index: 393983 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8196. Min Range: -6.8196
Max Act: 6.5071. Min Act: -0.1700
Data Index: 2109020 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8196. Min Range: -6.8196
Max Act: 6.5071. Min Act: -0.1700
Data Index: 7611831 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8196. Min Range: -6.8196
Max Act: 6.4446. Min Act: -0.1700
Data Index: 2364446 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8196. Min Range: -6.8196
Max Act: 6.2883. Min Act: -0.1700
Data Index: 208028 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8196. Min Range: -6.8196
Max Act: 6.2571. Min Act: -0.1700
Data Index: 8024 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8196. Min Range: -6.8196
Max Act: 6.2258. Min Act: -0.1700
Data Index: 8022 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8196. Min Range: -6.8196
Max Act: 6.2571. Min Act: -0.1700
Data Index: 2451502 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8196. Min Range: -6.8196
Max Act: 6.2258. Min Act: -0.1700
Data Index: 5827417 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8196. Min Range: -6.8196
Max Act: 6.1946. Min Act: -0.1700
Data Index: 6671840 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8196. Min Range: -6.8196
Max Act: 6.2258. Min Act: -0.1700
Data Index: 685445 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8196. Min Range: -6.8196
Max Act: 6.2258. Min Act: -0.1700
Data Index: 2440389 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8196. Min Range: -6.8196
Max Act: 6.1633. Min Act: -0.1700
Data Index: 8495071 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8196. Min Range: -6.8196
Max Act: 6.1946. Min Act: -0.1700
Data Index: 119927 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8196. Min Range: -6.8196
Max Act: 6.1946. Min Act: -0.1700
Data Index: 1291286 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8196. Min Range: -6.8196
Max Act: 6.1633. Min Act: -0.1700
Data Index: 2786146 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8196. Min Range: -6.8196
Max Act: 6.1633. Min Act: -0.1700
Data Index: 3727387 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8196. Min Range: -6.8196
Max Act: 6.1946. Min Act: -0.1700
Data Index: 1151444 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19