Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1984 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4499. Min Range: -8.4499
Max Act: 8.4499. Min Act: -0.1700
Data Index: 3191473 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4499. Min Range: -8.4499
Max Act: 8.3874. Min Act: -0.1700
Data Index: 6942037 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4499. Min Range: -8.4499
Max Act: 8.3874. Min Act: -0.1700
Data Index: 2125026 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4499. Min Range: -8.4499
Max Act: 8.1374. Min Act: -0.1700
Data Index: 8190456 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4499. Min Range: -8.4499
Max Act: 8.0749. Min Act: -0.1700
Data Index: 6338042 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.9186. Min Act: -0.1700
Data Index: 7060693 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.8874. Min Act: -0.1700
Data Index: 3036455 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.8561. Min Act: -0.1700
Data Index: 8000633 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.7936. Min Act: -0.1700
Data Index: 7591666 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.7936. Min Act: -0.1700
Data Index: 5844747 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.7936. Min Act: -0.1700
Data Index: 6338040 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.7936. Min Act: -0.1700
Data Index: 6382740 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.7936. Min Act: -0.1700
Data Index: 8190457 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.7624. Min Act: -0.1700
Data Index: 5157813 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.7311. Min Act: -0.1700
Data Index: 4527762 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.7311. Min Act: -0.1700
Data Index: 8000643 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.6686. Min Act: -0.1700
Data Index: 4527759 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.6999. Min Act: -0.1700
Data Index: 8000627 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.6999. Min Act: -0.1700
Data Index: 2125027 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.6374. Min Act: -0.1700
Data Index: 7591665 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19