Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6173 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3109. Min Range: -6.3109
Max Act: 6.3109. Min Act: -0.1700
Data Index: 8419637 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3109. Min Range: -6.3109
Max Act: 6.0921. Min Act: -0.1700
Data Index: 5546907 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3109. Min Range: -6.3109
Max Act: 6.0609. Min Act: -0.1700
Data Index: 6645026 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3109. Min Range: -6.3109
Max Act: 6.0296. Min Act: -0.1700
Data Index: 6082503 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3109. Min Range: -6.3109
Max Act: 5.9359. Min Act: -0.1700
Data Index: 1278265 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3109. Min Range: -6.3109
Max Act: 5.9359. Min Act: -0.1700
Data Index: 5546906 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3109. Min Range: -6.3109
Max Act: 5.9359. Min Act: -0.1700
Data Index: 171453 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3109. Min Range: -6.3109
Max Act: 5.7796. Min Act: -0.1700
Data Index: 1601417 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3109. Min Range: -6.3109
Max Act: 5.7484. Min Act: -0.1700
Data Index: 594211 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3109. Min Range: -6.3109
Max Act: 5.7171. Min Act: -0.1700
Data Index: 1635983 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3109. Min Range: -6.3109
Max Act: 5.7171. Min Act: -0.1700
Data Index: 4277430 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3109. Min Range: -6.3109
Max Act: 5.7484. Min Act: -0.1700
Data Index: 171455 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3109. Min Range: -6.3109
Max Act: 5.6859. Min Act: -0.1700
Data Index: 3346226 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3109. Min Range: -6.3109
Max Act: 5.6859. Min Act: -0.1700
Data Index: 8335417 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3109. Min Range: -6.3109
Max Act: 5.6859. Min Act: -0.1700
Data Index: 6667212 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3109. Min Range: -6.3109
Max Act: 5.5921. Min Act: -0.1700
Data Index: 3082659 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3109. Min Range: -6.3109
Max Act: 5.6234. Min Act: -0.1700
Data Index: 7997577 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3109. Min Range: -6.3109
Max Act: 5.6234. Min Act: -0.1700
Data Index: 5347456 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3109. Min Range: -6.3109
Max Act: 5.6234. Min Act: -0.1700
Data Index: 344476 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3109. Min Range: -6.3109
Max Act: 5.5921. Min Act: -0.1700
Data Index: 8424274 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19