Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4084 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4505. Min Range: -6.4505
Max Act: 6.4505. Min Act: -0.1700
Data Index: 468837 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4505. Min Range: -6.4505
Max Act: 6.2942. Min Act: -0.1700
Data Index: 468823 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4505. Min Range: -6.4505
Max Act: 6.2005. Min Act: -0.1700
Data Index: 2211482 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4505. Min Range: -6.4505
Max Act: 6.1380. Min Act: -0.1700
Data Index: 8617323 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4505. Min Range: -6.4505
Max Act: 6.1380. Min Act: -0.1700
Data Index: 4146362 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4505. Min Range: -6.4505
Max Act: 6.0442. Min Act: -0.1700
Data Index: 2189962 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4505. Min Range: -6.4505
Max Act: 5.9817. Min Act: -0.1700
Data Index: 2416788 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4505. Min Range: -6.4505
Max Act: 5.9505. Min Act: -0.1700
Data Index: 468832 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4505. Min Range: -6.4505
Max Act: 5.8880. Min Act: -0.1700
Data Index: 468825 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4505. Min Range: -6.4505
Max Act: 5.8880. Min Act: -0.1700
Data Index: 3575447 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4505. Min Range: -6.4505
Max Act: 5.8880. Min Act: -0.1700
Data Index: 8617335 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4505. Min Range: -6.4505
Max Act: 5.8567. Min Act: -0.1700
Data Index: 5228272 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4505. Min Range: -6.4505
Max Act: 5.8567. Min Act: -0.1700
Data Index: 2328384 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4505. Min Range: -6.4505
Max Act: 5.8567. Min Act: -0.1700
Data Index: 4098018 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4505. Min Range: -6.4505
Max Act: 5.8567. Min Act: -0.1700
Data Index: 6856220 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4505. Min Range: -6.4505
Max Act: 5.8255. Min Act: -0.1700
Data Index: 8123742 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4505. Min Range: -6.4505
Max Act: 5.8255. Min Act: -0.1700
Data Index: 3025174 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4505. Min Range: -6.4505
Max Act: 5.8255. Min Act: -0.1700
Data Index: 3232487 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4505. Min Range: -6.4505
Max Act: 5.7942. Min Act: -0.1700
Data Index: 3357132 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4505. Min Range: -6.4505
Max Act: 5.7630. Min Act: -0.1700
Data Index: 3735947 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19