Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4204 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9825. Min Range: -7.9825
Max Act: 7.9825. Min Act: -0.1700
Data Index: 7445382 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9825. Min Range: -7.9825
Max Act: 7.8263. Min Act: -0.1700
Data Index: 2684282 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9825. Min Range: -7.9825
Max Act: 7.5763. Min Act: -0.1700
Data Index: 4613155 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9825. Min Range: -7.9825
Max Act: 7.5763. Min Act: -0.1700
Data Index: 6956020 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9825. Min Range: -7.9825
Max Act: 7.5138. Min Act: -0.1700
Data Index: 3396602 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9825. Min Range: -7.9825
Max Act: 7.4200. Min Act: -0.1700
Data Index: 3331829 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9825. Min Range: -7.9825
Max Act: 7.4200. Min Act: -0.1700
Data Index: 4780081 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9825. Min Range: -7.9825
Max Act: 7.3888. Min Act: -0.1700
Data Index: 7914153 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9825. Min Range: -7.9825
Max Act: 7.3888. Min Act: -0.1700
Data Index: 1958586 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9825. Min Range: -7.9825
Max Act: 7.3575. Min Act: -0.1700
Data Index: 6924389 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9825. Min Range: -7.9825
Max Act: 7.3575. Min Act: -0.1700
Data Index: 6477130 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9825. Min Range: -7.9825
Max Act: 7.2638. Min Act: -0.1700
Data Index: 7080500 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9825. Min Range: -7.9825
Max Act: 7.2325. Min Act: -0.1700
Data Index: 6330310 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9825. Min Range: -7.9825
Max Act: 7.2325. Min Act: -0.1700
Data Index: 660295 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9825. Min Range: -7.9825
Max Act: 7.2325. Min Act: -0.1700
Data Index: 7079430 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9825. Min Range: -7.9825
Max Act: 7.2013. Min Act: -0.1700
Data Index: 2205161 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9825. Min Range: -7.9825
Max Act: 7.2013. Min Act: -0.1700
Data Index: 7018444 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9825. Min Range: -7.9825
Max Act: 7.2013. Min Act: -0.1700
Data Index: 7179860 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9825. Min Range: -7.9825
Max Act: 7.2013. Min Act: -0.1700
Data Index: 4977366 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9825. Min Range: -7.9825
Max Act: 7.2325. Min Act: -0.1700
Data Index: 4803110 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19