Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2656 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4681. Min Range: -6.4681
Max Act: 6.4681. Min Act: -0.1700
Data Index: 2449856 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4681. Min Range: -6.4681
Max Act: 6.3744. Min Act: -0.1700
Data Index: 1772688 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4681. Min Range: -6.4681
Max Act: 6.1556. Min Act: -0.1700
Data Index: 1875518 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4681. Min Range: -6.4681
Max Act: 6.0931. Min Act: -0.1700
Data Index: 8107331 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4681. Min Range: -6.4681
Max Act: 6.0306. Min Act: -0.1700
Data Index: 5588039 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4681. Min Range: -6.4681
Max Act: 6.0619. Min Act: -0.1700
Data Index: 8285729 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4681. Min Range: -6.4681
Max Act: 6.0306. Min Act: -0.1700
Data Index: 3302715 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4681. Min Range: -6.4681
Max Act: 6.0306. Min Act: -0.1700
Data Index: 4099304 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4681. Min Range: -6.4681
Max Act: 6.0306. Min Act: -0.1700
Data Index: 7130495 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4681. Min Range: -6.4681
Max Act: 5.9681. Min Act: -0.1700
Data Index: 2429770 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4681. Min Range: -6.4681
Max Act: 5.9994. Min Act: -0.1700
Data Index: 2248408 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4681. Min Range: -6.4681
Max Act: 5.9994. Min Act: -0.1700
Data Index: 3619200 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4681. Min Range: -6.4681
Max Act: 5.9681. Min Act: -0.1700
Data Index: 1289901 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4681. Min Range: -6.4681
Max Act: 5.9369. Min Act: -0.1700
Data Index: 8419534 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4681. Min Range: -6.4681
Max Act: 5.9369. Min Act: -0.1700
Data Index: 5326898 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4681. Min Range: -6.4681
Max Act: 5.9056. Min Act: -0.1700
Data Index: 5119441 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4681. Min Range: -6.4681
Max Act: 5.9056. Min Act: -0.1700
Data Index: 7786876 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4681. Min Range: -6.4681
Max Act: 5.9056. Min Act: -0.1700
Data Index: 4878659 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4681. Min Range: -6.4681
Max Act: 5.8744. Min Act: -0.1700
Data Index: 2180064 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4681. Min Range: -6.4681
Max Act: 5.8744. Min Act: -0.1700
Data Index: 1824774 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19