Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2968 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0623. Min Range: -5.0623
Max Act: 5.0623. Min Act: -0.1700
Data Index: 1630168 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0623. Min Range: -5.0623
Max Act: 4.9685. Min Act: -0.1700
Data Index: 1420727 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0623. Min Range: -5.0623
Max Act: 4.9373. Min Act: -0.1700
Data Index: 4228521 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0623. Min Range: -5.0623
Max Act: 4.9060. Min Act: -0.1700
Data Index: 8334966 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0623. Min Range: -5.0623
Max Act: 4.9060. Min Act: -0.1700
Data Index: 3842770 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0623. Min Range: -5.0623
Max Act: 4.8748. Min Act: -0.1700
Data Index: 5505882 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0623. Min Range: -5.0623
Max Act: 4.8748. Min Act: -0.1700
Data Index: 3590656 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0623. Min Range: -5.0623
Max Act: 4.8748. Min Act: -0.1700
Data Index: 2917910 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0623. Min Range: -5.0623
Max Act: 4.8435. Min Act: -0.1700
Data Index: 5891543 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0623. Min Range: -5.0623
Max Act: 4.8435. Min Act: -0.1700
Data Index: 6106607 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0623. Min Range: -5.0623
Max Act: 4.8435. Min Act: -0.1700
Data Index: 371123 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0623. Min Range: -5.0623
Max Act: 4.8435. Min Act: -0.1700
Data Index: 7997562 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0623. Min Range: -5.0623
Max Act: 4.8435. Min Act: -0.1700
Data Index: 5693782 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0623. Min Range: -5.0623
Max Act: 4.8123. Min Act: -0.1700
Data Index: 3592734 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0623. Min Range: -5.0623
Max Act: 4.7810. Min Act: -0.1700
Data Index: 8730044 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0623. Min Range: -5.0623
Max Act: 4.8123. Min Act: -0.1700
Data Index: 8112948 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0623. Min Range: -5.0623
Max Act: 4.7498. Min Act: -0.1700
Data Index: 3413532 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0623. Min Range: -5.0623
Max Act: 4.7498. Min Act: -0.1700
Data Index: 3139496 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0623. Min Range: -5.0623
Max Act: 4.7498. Min Act: -0.1700
Data Index: 7520865 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0623. Min Range: -5.0623
Max Act: 4.7185. Min Act: -0.1700
Data Index: 8077932 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19