Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1933 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5520. Min Range: -9.5520
Max Act: 9.5520. Min Act: -0.1700
Data Index: 3751963 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5520. Min Range: -9.5520
Max Act: 8.9270. Min Act: -0.1700
Data Index: 7144235 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5520. Min Range: -9.5520
Max Act: 8.8020. Min Act: -0.1700
Data Index: 7536020 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5520. Min Range: -9.5520
Max Act: 8.8020. Min Act: -0.1700
Data Index: 1454816 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5520. Min Range: -9.5520
Max Act: 8.6145. Min Act: -0.1700
Data Index: 5094885 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5520. Min Range: -9.5520
Max Act: 8.3645. Min Act: -0.1700
Data Index: 7787006 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5520. Min Range: -9.5520
Max Act: 8.3645. Min Act: -0.1700
Data Index: 5803843 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5520. Min Range: -9.5520
Max Act: 8.3020. Min Act: -0.1700
Data Index: 4287057 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5520. Min Range: -9.5520
Max Act: 8.3020. Min Act: -0.1700
Data Index: 480267 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5520. Min Range: -9.5520
Max Act: 8.2395. Min Act: -0.1700
Data Index: 2816694 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5520. Min Range: -9.5520
Max Act: 8.2395. Min Act: -0.1700
Data Index: 5761539 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5520. Min Range: -9.5520
Max Act: 8.1770. Min Act: -0.1700
Data Index: 2317157 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5520. Min Range: -9.5520
Max Act: 8.1770. Min Act: -0.1700
Data Index: 3451671 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5520. Min Range: -9.5520
Max Act: 8.1145. Min Act: -0.1700
Data Index: 6881189 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5520. Min Range: -9.5520
Max Act: 8.0520. Min Act: -0.1700
Data Index: 5521470 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5520. Min Range: -9.5520
Max Act: 8.0520. Min Act: -0.1700
Data Index: 140282 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5520. Min Range: -9.5520
Max Act: 8.0520. Min Act: -0.1700
Data Index: 6986718 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5520. Min Range: -9.5520
Max Act: 8.0520. Min Act: -0.1700
Data Index: 6621804 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5520. Min Range: -9.5520
Max Act: 7.9895. Min Act: -0.1700
Data Index: 1426077 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5520. Min Range: -9.5520
Max Act: 7.9895. Min Act: -0.1700
Data Index: 6572330 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19