Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3335 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0623. Min Range: -4.0623
Max Act: 4.0623. Min Act: -0.1700
Data Index: 3292043 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9997. Min Act: -0.1700
Data Index: 2212940 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9997. Min Act: -0.1700
Data Index: 3451477 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9685. Min Act: -0.1700
Data Index: 699282 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9685. Min Act: -0.1700
Data Index: 2145891 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9685. Min Act: -0.1700
Data Index: 6700944 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9685. Min Act: -0.1700
Data Index: 3947882 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9372. Min Act: -0.1700
Data Index: 7513004 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9372. Min Act: -0.1700
Data Index: 1657047 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9060. Min Act: -0.1700
Data Index: 5624875 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9060. Min Act: -0.1700
Data Index: 6568500 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8747. Min Act: -0.1700
Data Index: 7139514 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8747. Min Act: -0.1700
Data Index: 2561692 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8747. Min Act: -0.1700
Data Index: 1557338 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8434. Min Act: -0.1700
Data Index: 4126451 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8434. Min Act: -0.1700
Data Index: 8296483 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8434. Min Act: -0.1700
Data Index: 3787921 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8121. Min Act: -0.1700
Data Index: 3946660 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.7965. Min Act: -0.1700
Data Index: 444390 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8121. Min Act: -0.1700
Data Index: 1541548 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19