Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4602 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0707. Min Range: -6.0707
Max Act: 6.0707. Min Act: -0.1700
Data Index: 1311417 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0707. Min Range: -6.0707
Max Act: 6.0395. Min Act: -0.1700
Data Index: 6568804 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0707. Min Range: -6.0707
Max Act: 6.0082. Min Act: -0.1700
Data Index: 2933172 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0707. Min Range: -6.0707
Max Act: 5.9770. Min Act: -0.1700
Data Index: 8304189 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0707. Min Range: -6.0707
Max Act: 5.9770. Min Act: -0.1700
Data Index: 7249743 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0707. Min Range: -6.0707
Max Act: 5.9457. Min Act: -0.1700
Data Index: 6864540 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0707. Min Range: -6.0707
Max Act: 5.8832. Min Act: -0.1700
Data Index: 68620 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0707. Min Range: -6.0707
Max Act: 5.8832. Min Act: -0.1700
Data Index: 4899891 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0707. Min Range: -6.0707
Max Act: 5.8520. Min Act: -0.1700
Data Index: 522150 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0707. Min Range: -6.0707
Max Act: 5.8520. Min Act: -0.1700
Data Index: 8199616 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0707. Min Range: -6.0707
Max Act: 5.8207. Min Act: -0.1700
Data Index: 5236835 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0707. Min Range: -6.0707
Max Act: 5.8207. Min Act: -0.1700
Data Index: 8770512 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0707. Min Range: -6.0707
Max Act: 5.8207. Min Act: -0.1700
Data Index: 7088295 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0707. Min Range: -6.0707
Max Act: 5.8207. Min Act: -0.1700
Data Index: 2629541 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0707. Min Range: -6.0707
Max Act: 5.8207. Min Act: -0.1700
Data Index: 3888550 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0707. Min Range: -6.0707
Max Act: 5.8207. Min Act: -0.1700
Data Index: 7474175 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0707. Min Range: -6.0707
Max Act: 5.7895. Min Act: -0.1700
Data Index: 2020400 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0707. Min Range: -6.0707
Max Act: 5.7895. Min Act: -0.1700
Data Index: 5338842 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0707. Min Range: -6.0707
Max Act: 5.7895. Min Act: -0.1700
Data Index: 4535089 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0707. Min Range: -6.0707
Max Act: 5.7895. Min Act: -0.1700
Data Index: 5212070 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19