Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4945 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1607. Min Range: -10.1607
Max Act: 10.1607. Min Act: -0.1700
Data Index: 2226748 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1607. Min Range: -10.1607
Max Act: 9.9107. Min Act: -0.1700
Data Index: 1960397 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1607. Min Range: -10.1607
Max Act: 9.7232. Min Act: -0.1700
Data Index: 3323640 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1607. Min Range: -10.1607
Max Act: 9.7232. Min Act: -0.1700
Data Index: 1362500 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1607. Min Range: -10.1607
Max Act: 9.7232. Min Act: -0.1700
Data Index: 2687459 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1607. Min Range: -10.1607
Max Act: 9.6607. Min Act: -0.1700
Data Index: 3203147 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1607. Min Range: -10.1607
Max Act: 9.6607. Min Act: -0.1700
Data Index: 7115143 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1607. Min Range: -10.1607
Max Act: 9.6607. Min Act: -0.1700
Data Index: 2395104 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1607. Min Range: -10.1607
Max Act: 9.5357. Min Act: -0.1700
Data Index: 7976345 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1607. Min Range: -10.1607
Max Act: 9.6607. Min Act: -0.1700
Data Index: 6153287 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1607. Min Range: -10.1607
Max Act: 9.5357. Min Act: -0.1700
Data Index: 5717365 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1607. Min Range: -10.1607
Max Act: 9.5357. Min Act: -0.1700
Data Index: 5296636 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1607. Min Range: -10.1607
Max Act: 9.5357. Min Act: -0.1700
Data Index: 1519772 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1607. Min Range: -10.1607
Max Act: 9.4732. Min Act: -0.1700
Data Index: 3099612 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1607. Min Range: -10.1607
Max Act: 9.4732. Min Act: -0.1700
Data Index: 7275563 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1607. Min Range: -10.1607
Max Act: 9.4732. Min Act: -0.1700
Data Index: 7217798 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1607. Min Range: -10.1607
Max Act: 9.4107. Min Act: -0.1700
Data Index: 966708 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1607. Min Range: -10.1607
Max Act: 9.4107. Min Act: -0.1700
Data Index: 5750729 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1607. Min Range: -10.1607
Max Act: 9.4107. Min Act: -0.1627
Data Index: 3054132 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1607. Min Range: -10.1607
Max Act: 9.4107. Min Act: -0.1700
Data Index: 3256444 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19