Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3297 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2777. Min Range: -7.2777
Max Act: 7.2777. Min Act: -0.1700
Data Index: 1687873 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2777. Min Range: -7.2777
Max Act: 7.0277. Min Act: -0.1700
Data Index: 8107851 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2777. Min Range: -7.2777
Max Act: 6.7777. Min Act: -0.1700
Data Index: 2405357 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2777. Min Range: -7.2777
Max Act: 6.6527. Min Act: -0.1700
Data Index: 1707347 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2777. Min Range: -7.2777
Max Act: 6.6527. Min Act: -0.1700
Data Index: 5697001 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2777. Min Range: -7.2777
Max Act: 6.6214. Min Act: -0.1700
Data Index: 1687871 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2777. Min Range: -7.2777
Max Act: 6.5589. Min Act: -0.1700
Data Index: 6152863 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2777. Min Range: -7.2777
Max Act: 6.5589. Min Act: -0.1700
Data Index: 3431271 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2777. Min Range: -7.2777
Max Act: 6.5277. Min Act: -0.1700
Data Index: 3644553 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2777. Min Range: -7.2777
Max Act: 6.4964. Min Act: -0.1700
Data Index: 6140677 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2777. Min Range: -7.2777
Max Act: 6.4964. Min Act: -0.1700
Data Index: 4834383 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2777. Min Range: -7.2777
Max Act: 6.4652. Min Act: -0.1700
Data Index: 5842410 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2777. Min Range: -7.2777
Max Act: 6.4652. Min Act: -0.1700
Data Index: 686709 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2777. Min Range: -7.2777
Max Act: 6.4964. Min Act: -0.1700
Data Index: 4091661 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2777. Min Range: -7.2777
Max Act: 6.4027. Min Act: -0.1700
Data Index: 3251702 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2777. Min Range: -7.2777
Max Act: 6.3714. Min Act: -0.1700
Data Index: 5472064 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2777. Min Range: -7.2777
Max Act: 6.4027. Min Act: -0.1700
Data Index: 4542155 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2777. Min Range: -7.2777
Max Act: 6.4027. Min Act: -0.1700
Data Index: 229614 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2777. Min Range: -7.2777
Max Act: 6.3714. Min Act: -0.1700
Data Index: 6300019 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2777. Min Range: -7.2777
Max Act: 6.3714. Min Act: -0.1700
Data Index: 1454047 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19