Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5312 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2143. Min Range: -5.2143
Max Act: 5.2143. Min Act: -0.1700
Data Index: 6296402 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2143. Min Range: -5.2143
Max Act: 5.1518. Min Act: -0.1700
Data Index: 5458225 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2143. Min Range: -5.2143
Max Act: 5.1205. Min Act: -0.1700
Data Index: 327360 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2143. Min Range: -5.2143
Max Act: 5.0893. Min Act: -0.1700
Data Index: 816251 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2143. Min Range: -5.2143
Max Act: 5.0893. Min Act: -0.1700
Data Index: 7031032 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2143. Min Range: -5.2143
Max Act: 5.0893. Min Act: -0.1700
Data Index: 198102 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2143. Min Range: -5.2143
Max Act: 5.0580. Min Act: -0.1700
Data Index: 6929595 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2143. Min Range: -5.2143
Max Act: 5.0580. Min Act: -0.1700
Data Index: 7093465 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2143. Min Range: -5.2143
Max Act: 5.0580. Min Act: -0.1700
Data Index: 1587289 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.9643. Min Act: -0.1700
Data Index: 6038763 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2143. Min Range: -5.2143
Max Act: 5.0268. Min Act: -0.1700
Data Index: 1322453 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.9643. Min Act: -0.1700
Data Index: 5515473 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.9643. Min Act: -0.1700
Data Index: 1177286 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.9018. Min Act: -0.1700
Data Index: 4807251 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.9330. Min Act: -0.1700
Data Index: 6109812 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.9643. Min Act: -0.1700
Data Index: 1315778 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.9018. Min Act: -0.1700
Data Index: 1326841 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.9018. Min Act: -0.1700
Data Index: 6458792 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.9018. Min Act: -0.1700
Data Index: 1811601 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.9018. Min Act: -0.1700
Data Index: 6709763 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19