Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2877 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1570. Min Range: -8.1570
Max Act: 8.1570. Min Act: -0.1700
Data Index: 3128694 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1570. Min Range: -8.1570
Max Act: 7.7820. Min Act: -0.1700
Data Index: 5685123 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1570. Min Range: -8.1570
Max Act: 7.6883. Min Act: -0.1700
Data Index: 7399747 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1570. Min Range: -8.1570
Max Act: 7.6883. Min Act: -0.1700
Data Index: 4125878 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1570. Min Range: -8.1570
Max Act: 7.6570. Min Act: -0.1700
Data Index: 2484035 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1570. Min Range: -8.1570
Max Act: 7.6258. Min Act: -0.1700
Data Index: 7502519 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1570. Min Range: -8.1570
Max Act: 7.6258. Min Act: -0.1700
Data Index: 8667026 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1570. Min Range: -8.1570
Max Act: 7.5945. Min Act: -0.1700
Data Index: 4065612 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1570. Min Range: -8.1570
Max Act: 7.5320. Min Act: -0.1700
Data Index: 7002049 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1570. Min Range: -8.1570
Max Act: 7.5633. Min Act: -0.1700
Data Index: 7305416 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1570. Min Range: -8.1570
Max Act: 7.5633. Min Act: -0.1700
Data Index: 4172091 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1570. Min Range: -8.1570
Max Act: 7.5008. Min Act: -0.1700
Data Index: 4836665 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1570. Min Range: -8.1570
Max Act: 7.5008. Min Act: -0.1700
Data Index: 6198070 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1570. Min Range: -8.1570
Max Act: 7.5008. Min Act: -0.1700
Data Index: 2580294 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1570. Min Range: -8.1570
Max Act: 7.4695. Min Act: -0.1700
Data Index: 5308320 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1570. Min Range: -8.1570
Max Act: 7.4695. Min Act: -0.1700
Data Index: 1890681 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1570. Min Range: -8.1570
Max Act: 7.4695. Min Act: -0.1700
Data Index: 3872667 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1570. Min Range: -8.1570
Max Act: 7.4383. Min Act: -0.1700
Data Index: 8497314 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1570. Min Range: -8.1570
Max Act: 7.3758. Min Act: -0.1700
Data Index: 4452826 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1570. Min Range: -8.1570
Max Act: 7.3758. Min Act: -0.1700
Data Index: 5584467 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19