Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3232 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9528. Min Range: -6.9528
Max Act: 6.9528. Min Act: -0.1700
Data Index: 2062154 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9528. Min Range: -6.9528
Max Act: 6.9215. Min Act: -0.1700
Data Index: 8707298 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9528. Min Range: -6.9528
Max Act: 6.8278. Min Act: -0.1700
Data Index: 2187412 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9528. Min Range: -6.9528
Max Act: 6.7965. Min Act: -0.1700
Data Index: 7090644 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9528. Min Range: -6.9528
Max Act: 6.7028. Min Act: -0.1700
Data Index: 6217332 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9528. Min Range: -6.9528
Max Act: 6.6090. Min Act: -0.1700
Data Index: 6955984 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9528. Min Range: -6.9528
Max Act: 6.5778. Min Act: -0.1700
Data Index: 4775305 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9528. Min Range: -6.9528
Max Act: 6.5465. Min Act: -0.1700
Data Index: 1556388 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9528. Min Range: -6.9528
Max Act: 6.4840. Min Act: -0.1700
Data Index: 2263752 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9528. Min Range: -6.9528
Max Act: 6.3903. Min Act: -0.1700
Data Index: 776349 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9528. Min Range: -6.9528
Max Act: 6.3590. Min Act: -0.1700
Data Index: 4778637 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9528. Min Range: -6.9528
Max Act: 6.3903. Min Act: -0.1700
Data Index: 5777495 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9528. Min Range: -6.9528
Max Act: 6.3590. Min Act: -0.1700
Data Index: 4865585 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9528. Min Range: -6.9528
Max Act: 6.3278. Min Act: -0.1700
Data Index: 4360537 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9528. Min Range: -6.9528
Max Act: 6.2965. Min Act: -0.1700
Data Index: 6826784 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9528. Min Range: -6.9528
Max Act: 6.3278. Min Act: -0.1700
Data Index: 997244 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9528. Min Range: -6.9528
Max Act: 6.2653. Min Act: -0.1700
Data Index: 3027119 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9528. Min Range: -6.9528
Max Act: 6.2965. Min Act: -0.1700
Data Index: 8579084 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9528. Min Range: -6.9528
Max Act: 6.2965. Min Act: -0.1700
Data Index: 7418322 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9528. Min Range: -6.9528
Max Act: 6.3278. Min Act: -0.1700
Data Index: 4055870 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19