Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2916 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1403. Min Range: -8.1403
Max Act: 8.1403. Min Act: -0.1700
Data Index: 1987480 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1403. Min Range: -8.1403
Max Act: 8.0778. Min Act: -0.1700
Data Index: 4915364 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1403. Min Range: -8.1403
Max Act: 8.0778. Min Act: -0.1700
Data Index: 8285678 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1403. Min Range: -8.1403
Max Act: 7.8590. Min Act: -0.1700
Data Index: 2282106 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1403. Min Range: -8.1403
Max Act: 7.8278. Min Act: -0.1700
Data Index: 387828 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1403. Min Range: -8.1403
Max Act: 7.7653. Min Act: -0.1700
Data Index: 3088088 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1403. Min Range: -8.1403
Max Act: 7.7028. Min Act: -0.1700
Data Index: 2977172 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1403. Min Range: -8.1403
Max Act: 7.6403. Min Act: -0.1700
Data Index: 2186374 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1403. Min Range: -8.1403
Max Act: 7.6403. Min Act: -0.1700
Data Index: 8453989 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1403. Min Range: -8.1403
Max Act: 7.6403. Min Act: -0.1700
Data Index: 461057 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1403. Min Range: -8.1403
Max Act: 7.6090. Min Act: -0.1700
Data Index: 905427 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1403. Min Range: -8.1403
Max Act: 7.5778. Min Act: -0.1700
Data Index: 1561380 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1403. Min Range: -8.1403
Max Act: 7.5778. Min Act: -0.1700
Data Index: 6847452 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1403. Min Range: -8.1403
Max Act: 7.5778. Min Act: -0.1700
Data Index: 5082091 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1403. Min Range: -8.1403
Max Act: 7.5153. Min Act: -0.1700
Data Index: 7153654 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1403. Min Range: -8.1403
Max Act: 7.5153. Min Act: -0.1700
Data Index: 4946845 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1403. Min Range: -8.1403
Max Act: 7.4840. Min Act: -0.1700
Data Index: 1141887 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1403. Min Range: -8.1403
Max Act: 7.4840. Min Act: -0.1700
Data Index: 377983 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1403. Min Range: -8.1403
Max Act: 7.4215. Min Act: -0.1700
Data Index: 2763448 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1403. Min Range: -8.1403
Max Act: 7.4528. Min Act: -0.1700
Data Index: 4724119 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19