Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3115 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.6316. Min Act: -0.1700
Data Index: 3245289 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.5691. Min Act: -0.1700
Data Index: 5483524 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.4129. Min Act: -0.1700
Data Index: 152741 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.3504. Min Act: -0.1700
Data Index: 3689485 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.2879. Min Act: -0.1700
Data Index: 3774852 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.2879. Min Act: -0.1700
Data Index: 515494 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.2566. Min Act: -0.1700
Data Index: 8177832 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.2254. Min Act: -0.1700
Data Index: 2211714 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.1629. Min Act: -0.1700
Data Index: 7511622 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.1316. Min Act: -0.1700
Data Index: 736255 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.1004. Min Act: -0.1700
Data Index: 1217939 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.0691. Min Act: -0.1700
Data Index: 7316334 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.0691. Min Act: -0.1700
Data Index: 6275512 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.0691. Min Act: -0.1700
Data Index: 581034 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.0691. Min Act: -0.1700
Data Index: 7687775 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.0379. Min Act: -0.1700
Data Index: 5784598 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.0379. Min Act: -0.1700
Data Index: 8040246 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.0379. Min Act: -0.1700
Data Index: 3289230 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.0379. Min Act: -0.1700
Data Index: 3366696 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.0379. Min Act: -0.1700
Data Index: 7619284 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19