Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3519 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4878. Min Range: -7.4878
Max Act: 7.4878. Min Act: -0.1700
Data Index: 897282 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4878. Min Range: -7.4878
Max Act: 6.6440. Min Act: -0.1700
Data Index: 5868032 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4878. Min Range: -7.4878
Max Act: 6.6440. Min Act: -0.1700
Data Index: 401050 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4878. Min Range: -7.4878
Max Act: 6.5815. Min Act: -0.1700
Data Index: 729118 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4878. Min Range: -7.4878
Max Act: 6.5815. Min Act: -0.1700
Data Index: 6955609 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4878. Min Range: -7.4878
Max Act: 6.5503. Min Act: -0.1700
Data Index: 7460836 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4878. Min Range: -7.4878
Max Act: 6.5503. Min Act: -0.1700
Data Index: 4382960 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4878. Min Range: -7.4878
Max Act: 6.5190. Min Act: -0.1700
Data Index: 4982442 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4878. Min Range: -7.4878
Max Act: 6.4878. Min Act: -0.1700
Data Index: 2272133 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4878. Min Range: -7.4878
Max Act: 6.4565. Min Act: -0.1700
Data Index: 3160593 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4878. Min Range: -7.4878
Max Act: 6.4253. Min Act: -0.1700
Data Index: 3646213 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4878. Min Range: -7.4878
Max Act: 6.3315. Min Act: -0.1700
Data Index: 781299 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4878. Min Range: -7.4878
Max Act: 6.3315. Min Act: -0.1700
Data Index: 5413053 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4878. Min Range: -7.4878
Max Act: 6.3003. Min Act: -0.1700
Data Index: 2696889 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4878. Min Range: -7.4878
Max Act: 6.3003. Min Act: -0.1700
Data Index: 2204730 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4878. Min Range: -7.4878
Max Act: 6.2690. Min Act: -0.1700
Data Index: 736849 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4878. Min Range: -7.4878
Max Act: 6.3003. Min Act: -0.1700
Data Index: 8617362 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4878. Min Range: -7.4878
Max Act: 6.2690. Min Act: -0.1700
Data Index: 5814827 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4878. Min Range: -7.4878
Max Act: 6.2690. Min Act: -0.1700
Data Index: 3384895 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4878. Min Range: -7.4878
Max Act: 6.2378. Min Act: -0.1700
Data Index: 2175410 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19