Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4585 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1480. Min Range: -9.1480
Max Act: 9.1480. Min Act: -0.1700
Data Index: 1616546 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1480. Min Range: -9.1480
Max Act: 8.3980. Min Act: -0.1700
Data Index: 1585013 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1480. Min Range: -9.1480
Max Act: 7.8355. Min Act: -0.1700
Data Index: 36532 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1480. Min Range: -9.1480
Max Act: 7.5542. Min Act: -0.1700
Data Index: 4302856 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1480. Min Range: -9.1480
Max Act: 7.5230. Min Act: -0.1700
Data Index: 2782459 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1480. Min Range: -9.1480
Max Act: 7.5542. Min Act: -0.1700
Data Index: 4088929 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1480. Min Range: -9.1480
Max Act: 7.5542. Min Act: -0.1700
Data Index: 4357877 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1480. Min Range: -9.1480
Max Act: 7.5230. Min Act: -0.1700
Data Index: 25137 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1480. Min Range: -9.1480
Max Act: 7.4917. Min Act: -0.1700
Data Index: 1967906 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1480. Min Range: -9.1480
Max Act: 7.5230. Min Act: -0.1700
Data Index: 6578958 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1480. Min Range: -9.1480
Max Act: 7.4605. Min Act: -0.1700
Data Index: 2723016 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1480. Min Range: -9.1480
Max Act: 7.3355. Min Act: -0.1700
Data Index: 715704 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1480. Min Range: -9.1480
Max Act: 7.3355. Min Act: -0.1700
Data Index: 6205415 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1480. Min Range: -9.1480
Max Act: 7.3042. Min Act: -0.1700
Data Index: 6911146 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1480. Min Range: -9.1480
Max Act: 7.2730. Min Act: -0.1700
Data Index: 6046387 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1480. Min Range: -9.1480
Max Act: 7.2730. Min Act: -0.1700
Data Index: 5800736 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1480. Min Range: -9.1480
Max Act: 7.2730. Min Act: -0.1700
Data Index: 6115434 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1480. Min Range: -9.1480
Max Act: 7.2417. Min Act: -0.1700
Data Index: 2227863 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1480. Min Range: -9.1480
Max Act: 7.2417. Min Act: -0.1700
Data Index: 6576894 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1480. Min Range: -9.1480
Max Act: 7.2105. Min Act: -0.1700
Data Index: 3787592 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19