Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 683 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7828. Min Range: -5.7828
Max Act: 5.7828. Min Act: -0.1700
Data Index: 1411599 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7828. Min Range: -5.7828
Max Act: 5.5953. Min Act: -0.1700
Data Index: 2925540 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7828. Min Range: -5.7828
Max Act: 5.3453. Min Act: -0.1700
Data Index: 7107214 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7828. Min Range: -5.7828
Max Act: 5.2203. Min Act: -0.1700
Data Index: 2362503 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7828. Min Range: -5.7828
Max Act: 5.2203. Min Act: -0.1700
Data Index: 1190821 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7828. Min Range: -5.7828
Max Act: 5.1891. Min Act: -0.1700
Data Index: 759293 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7828. Min Range: -5.7828
Max Act: 5.1578. Min Act: -0.1700
Data Index: 5840981 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7828. Min Range: -5.7828
Max Act: 5.0953. Min Act: -0.1700
Data Index: 1989382 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7828. Min Range: -5.7828
Max Act: 5.0953. Min Act: -0.1700
Data Index: 337243 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7828. Min Range: -5.7828
Max Act: 5.0328. Min Act: -0.1700
Data Index: 4990512 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7828. Min Range: -5.7828
Max Act: 5.0016. Min Act: -0.1700
Data Index: 2640983 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7828. Min Range: -5.7828
Max Act: 5.0016. Min Act: -0.1700
Data Index: 7669963 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7828. Min Range: -5.7828
Max Act: 5.0016. Min Act: -0.1700
Data Index: 8373393 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7828. Min Range: -5.7828
Max Act: 4.9078. Min Act: -0.1700
Data Index: 7742756 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7828. Min Range: -5.7828
Max Act: 4.9391. Min Act: -0.1700
Data Index: 2334949 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7828. Min Range: -5.7828
Max Act: 4.9078. Min Act: -0.1700
Data Index: 3612112 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7828. Min Range: -5.7828
Max Act: 4.8766. Min Act: -0.1700
Data Index: 6223158 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7828. Min Range: -5.7828
Max Act: 4.9078. Min Act: -0.1700
Data Index: 5006953 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7828. Min Range: -5.7828
Max Act: 4.8766. Min Act: -0.1700
Data Index: 7185284 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7828. Min Range: -5.7828
Max Act: 4.8766. Min Act: -0.1700
Data Index: 3556673 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19