Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3491 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3069. Min Range: -7.3069
Max Act: 7.3069. Min Act: -0.1700
Data Index: 363194 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3069. Min Range: -7.3069
Max Act: 7.2757. Min Act: -0.1700
Data Index: 5997091 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3069. Min Range: -7.3069
Max Act: 7.1194. Min Act: -0.1700
Data Index: 2352306 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3069. Min Range: -7.3069
Max Act: 7.0569. Min Act: -0.1700
Data Index: 6534905 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3069. Min Range: -7.3069
Max Act: 7.0257. Min Act: -0.1700
Data Index: 5272245 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3069. Min Range: -7.3069
Max Act: 6.9632. Min Act: -0.1700
Data Index: 7708207 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3069. Min Range: -7.3069
Max Act: 6.9319. Min Act: -0.1700
Data Index: 7383577 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3069. Min Range: -7.3069
Max Act: 6.9319. Min Act: -0.1700
Data Index: 6534902 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3069. Min Range: -7.3069
Max Act: 6.9007. Min Act: -0.1700
Data Index: 6390856 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3069. Min Range: -7.3069
Max Act: 6.9319. Min Act: -0.1700
Data Index: 2489453 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3069. Min Range: -7.3069
Max Act: 6.9007. Min Act: -0.1700
Data Index: 1209764 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3069. Min Range: -7.3069
Max Act: 6.9007. Min Act: -0.1700
Data Index: 5855628 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3069. Min Range: -7.3069
Max Act: 6.8694. Min Act: -0.1700
Data Index: 5738091 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3069. Min Range: -7.3069
Max Act: 6.8694. Min Act: -0.1700
Data Index: 7599162 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3069. Min Range: -7.3069
Max Act: 6.8069. Min Act: -0.1700
Data Index: 363195 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3069. Min Range: -7.3069
Max Act: 6.8069. Min Act: -0.1700
Data Index: 4200363 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3069. Min Range: -7.3069
Max Act: 6.7757. Min Act: -0.1700
Data Index: 5164779 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3069. Min Range: -7.3069
Max Act: 6.7757. Min Act: -0.1700
Data Index: 7022979 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3069. Min Range: -7.3069
Max Act: 6.7757. Min Act: -0.1700
Data Index: 6562268 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3069. Min Range: -7.3069
Max Act: 6.8069. Min Act: -0.1700
Data Index: 3051510 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19