Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3458 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1466. Min Range: -6.1466
Max Act: 6.1466. Min Act: -0.1700
Data Index: 1696253 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1466. Min Range: -6.1466
Max Act: 5.7403. Min Act: -0.1700
Data Index: 1501996 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1466. Min Range: -6.1466
Max Act: 5.7403. Min Act: -0.1700
Data Index: 903593 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1466. Min Range: -6.1466
Max Act: 5.7091. Min Act: -0.1700
Data Index: 992648 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1466. Min Range: -6.1466
Max Act: 5.6778. Min Act: -0.1700
Data Index: 1461927 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1466. Min Range: -6.1466
Max Act: 5.6778. Min Act: -0.1700
Data Index: 5241654 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1466. Min Range: -6.1466
Max Act: 5.6466. Min Act: -0.1700
Data Index: 11844 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1466. Min Range: -6.1466
Max Act: 5.6466. Min Act: -0.1700
Data Index: 8569001 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1466. Min Range: -6.1466
Max Act: 5.6466. Min Act: -0.1700
Data Index: 2024447 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1466. Min Range: -6.1466
Max Act: 5.6153. Min Act: -0.1700
Data Index: 2792652 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1466. Min Range: -6.1466
Max Act: 5.5528. Min Act: -0.1700
Data Index: 6786875 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1466. Min Range: -6.1466
Max Act: 5.5528. Min Act: -0.1700
Data Index: 4429641 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1466. Min Range: -6.1466
Max Act: 5.5528. Min Act: -0.1700
Data Index: 5364575 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1466. Min Range: -6.1466
Max Act: 5.5528. Min Act: -0.1700
Data Index: 158400 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1466. Min Range: -6.1466
Max Act: 5.5528. Min Act: -0.1700
Data Index: 2004683 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1466. Min Range: -6.1466
Max Act: 5.5216. Min Act: -0.1700
Data Index: 1498305 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1466. Min Range: -6.1466
Max Act: 5.5216. Min Act: -0.1700
Data Index: 3585363 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1466. Min Range: -6.1466
Max Act: 5.4903. Min Act: -0.1700
Data Index: 1001360 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1466. Min Range: -6.1466
Max Act: 5.4903. Min Act: -0.1700
Data Index: 4271214 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1466. Min Range: -6.1466
Max Act: 5.4278. Min Act: -0.1700
Data Index: 4062664 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19