Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1336 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5711. Min Range: -7.5711
Max Act: 7.5711. Min Act: -0.1700
Data Index: 3516855 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5711. Min Range: -7.5711
Max Act: 7.4773. Min Act: -0.1700
Data Index: 8774034 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5711. Min Range: -7.5711
Max Act: 7.4773. Min Act: -0.1700
Data Index: 77444 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5711. Min Range: -7.5711
Max Act: 7.4773. Min Act: -0.1700
Data Index: 3811693 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5711. Min Range: -7.5711
Max Act: 7.3836. Min Act: -0.1700
Data Index: 5435271 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5711. Min Range: -7.5711
Max Act: 7.3211. Min Act: -0.1700
Data Index: 7696507 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5711. Min Range: -7.5711
Max Act: 7.3523. Min Act: -0.1700
Data Index: 993973 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5711. Min Range: -7.5711
Max Act: 7.2898. Min Act: -0.1700
Data Index: 7420042 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5711. Min Range: -7.5711
Max Act: 7.2586. Min Act: -0.1700
Data Index: 86379 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5711. Min Range: -7.5711
Max Act: 7.2586. Min Act: -0.1700
Data Index: 7621974 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5711. Min Range: -7.5711
Max Act: 7.2273. Min Act: -0.1700
Data Index: 4212452 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5711. Min Range: -7.5711
Max Act: 7.1961. Min Act: -0.1700
Data Index: 4234666 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5711. Min Range: -7.5711
Max Act: 7.2273. Min Act: -0.1700
Data Index: 4282056 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5711. Min Range: -7.5711
Max Act: 7.1961. Min Act: -0.1700
Data Index: 107010 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5711. Min Range: -7.5711
Max Act: 7.1961. Min Act: -0.1700
Data Index: 7922296 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5711. Min Range: -7.5711
Max Act: 7.1336. Min Act: -0.1700
Data Index: 1301974 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5711. Min Range: -7.5711
Max Act: 7.1336. Min Act: -0.1700
Data Index: 3755574 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5711. Min Range: -7.5711
Max Act: 7.1336. Min Act: -0.1700
Data Index: 2999390 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5711. Min Range: -7.5711
Max Act: 7.1023. Min Act: -0.1700
Data Index: 1945600 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5711. Min Range: -7.5711
Max Act: 7.0398. Min Act: -0.1700
Data Index: 6962991 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19