Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6385 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.4825. Min Act: -0.1700
Data Index: 599254 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.4200. Min Act: -0.1700
Data Index: 3666668 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.3575. Min Act: -0.1700
Data Index: 4413450 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.2638. Min Act: -0.1700
Data Index: 6996108 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.2013. Min Act: -0.1700
Data Index: 6571034 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.2325. Min Act: -0.1700
Data Index: 7516539 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.2325. Min Act: -0.1700
Data Index: 70090 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.2325. Min Act: -0.1700
Data Index: 3050240 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.2325. Min Act: -0.1700
Data Index: 937307 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.1700. Min Act: -0.1700
Data Index: 3923609 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.1388. Min Act: -0.1700
Data Index: 2277830 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.1388. Min Act: -0.1700
Data Index: 3419074 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.1075. Min Act: -0.1700
Data Index: 1077835 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.1075. Min Act: -0.1700
Data Index: 6702341 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.1075. Min Act: -0.1700
Data Index: 1403857 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.1075. Min Act: -0.1700
Data Index: 132201 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.0763. Min Act: -0.1700
Data Index: 8026626 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.0763. Min Act: -0.1700
Data Index: 5647729 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.0450. Min Act: -0.1700
Data Index: 5653718 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.0138. Min Act: -0.1700
Data Index: 2512286 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19