Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5017 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8588. Min Range: -3.8588
Max Act: 3.8588. Min Act: -0.1700
Data Index: 3097817 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8588. Min Range: -3.8588
Max Act: 3.6398. Min Act: -0.1700
Data Index: 1953343 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8588. Min Range: -3.8588
Max Act: 3.5928. Min Act: -0.1700
Data Index: 4581850 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8588. Min Range: -3.8588
Max Act: 3.5772. Min Act: -0.1700
Data Index: 3103297 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8588. Min Range: -3.8588
Max Act: 3.5772. Min Act: -0.1700
Data Index: 4464547 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8588. Min Range: -3.8588
Max Act: 3.5459. Min Act: -0.1700
Data Index: 5319168 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8588. Min Range: -3.8588
Max Act: 3.5615. Min Act: -0.1700
Data Index: 5149397 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8588. Min Range: -3.8588
Max Act: 3.5615. Min Act: -0.1700
Data Index: 3447071 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8588. Min Range: -3.8588
Max Act: 3.5459. Min Act: -0.1700
Data Index: 1018302 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8588. Min Range: -3.8588
Max Act: 3.5459. Min Act: -0.1700
Data Index: 1983660 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8588. Min Range: -3.8588
Max Act: 3.5146. Min Act: -0.1700
Data Index: 3464409 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8588. Min Range: -3.8588
Max Act: 3.5146. Min Act: -0.1700
Data Index: 2667223 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8588. Min Range: -3.8588
Max Act: 3.5146. Min Act: -0.1700
Data Index: 5554984 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8588. Min Range: -3.8588
Max Act: 3.4832. Min Act: -0.1700
Data Index: 1947859 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8588. Min Range: -3.8588
Max Act: 3.4832. Min Act: -0.1700
Data Index: 6338902 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8588. Min Range: -3.8588
Max Act: 3.4676. Min Act: -0.1700
Data Index: 7412747 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8588. Min Range: -3.8588
Max Act: 3.4832. Min Act: -0.1700
Data Index: 3923487 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8588. Min Range: -3.8588
Max Act: 3.4519. Min Act: -0.1700
Data Index: 1340155 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8588. Min Range: -3.8588
Max Act: 3.4362. Min Act: -0.1700
Data Index: 3036470 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8588. Min Range: -3.8588
Max Act: 3.4362. Min Act: -0.1700
Data Index: 1032802 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19