Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2634 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4974. Min Range: -6.4974
Max Act: 6.4974. Min Act: -0.1700
Data Index: 7097165 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4974. Min Range: -6.4974
Max Act: 5.6849. Min Act: -0.1700
Data Index: 937170 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4974. Min Range: -6.4974
Max Act: 5.6536. Min Act: -0.1700
Data Index: 6098431 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4974. Min Range: -6.4974
Max Act: 5.5911. Min Act: -0.1700
Data Index: 8015169 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4974. Min Range: -6.4974
Max Act: 5.4974. Min Act: -0.1700
Data Index: 2421262 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4974. Min Range: -6.4974
Max Act: 5.4661. Min Act: -0.1700
Data Index: 5677512 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4974. Min Range: -6.4974
Max Act: 5.4036. Min Act: -0.1700
Data Index: 2990142 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4974. Min Range: -6.4974
Max Act: 5.3724. Min Act: -0.1700
Data Index: 3046986 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4974. Min Range: -6.4974
Max Act: 5.3411. Min Act: -0.1700
Data Index: 2192168 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4974. Min Range: -6.4974
Max Act: 5.3099. Min Act: -0.1700
Data Index: 8608942 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4974. Min Range: -6.4974
Max Act: 5.2474. Min Act: -0.1700
Data Index: 8042174 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4974. Min Range: -6.4974
Max Act: 5.2161. Min Act: -0.1700
Data Index: 5930470 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4974. Min Range: -6.4974
Max Act: 5.2161. Min Act: -0.1700
Data Index: 5654923 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4974. Min Range: -6.4974
Max Act: 5.2161. Min Act: -0.1700
Data Index: 213046 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4974. Min Range: -6.4974
Max Act: 5.1849. Min Act: -0.1700
Data Index: 4450022 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4974. Min Range: -6.4974
Max Act: 5.2161. Min Act: -0.1700
Data Index: 1357091 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4974. Min Range: -6.4974
Max Act: 5.1224. Min Act: -0.1700
Data Index: 1207659 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4974. Min Range: -6.4974
Max Act: 5.1224. Min Act: -0.1700
Data Index: 7331229 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4974. Min Range: -6.4974
Max Act: 5.1536. Min Act: -0.1700
Data Index: 4945722 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4974. Min Range: -6.4974
Max Act: 5.1536. Min Act: -0.1700
Data Index: 6327320 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19