Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2606 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5300. Min Range: -8.5300
Max Act: 8.5300. Min Act: -0.1700
Data Index: 8047841 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5300. Min Range: -8.5300
Max Act: 8.2175. Min Act: -0.1700
Data Index: 6742810 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5300. Min Range: -8.5300
Max Act: 8.1550. Min Act: -0.1700
Data Index: 4874116 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5300. Min Range: -8.5300
Max Act: 8.1237. Min Act: -0.1700
Data Index: 6143230 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5300. Min Range: -8.5300
Max Act: 7.9987. Min Act: -0.1700
Data Index: 3372570 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5300. Min Range: -8.5300
Max Act: 7.9675. Min Act: -0.1700
Data Index: 5516582 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5300. Min Range: -8.5300
Max Act: 7.9675. Min Act: -0.1700
Data Index: 3003944 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5300. Min Range: -8.5300
Max Act: 7.9675. Min Act: -0.1700
Data Index: 2948987 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5300. Min Range: -8.5300
Max Act: 7.8737. Min Act: -0.1700
Data Index: 5620437 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5300. Min Range: -8.5300
Max Act: 7.8425. Min Act: -0.1700
Data Index: 2406022 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5300. Min Range: -8.5300
Max Act: 7.8425. Min Act: -0.1700
Data Index: 772131 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5300. Min Range: -8.5300
Max Act: 7.8425. Min Act: -0.1700
Data Index: 4549809 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5300. Min Range: -8.5300
Max Act: 7.8112. Min Act: -0.1700
Data Index: 2429402 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5300. Min Range: -8.5300
Max Act: 7.7487. Min Act: -0.1700
Data Index: 5453395 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5300. Min Range: -8.5300
Max Act: 7.7487. Min Act: -0.1700
Data Index: 5879523 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5300. Min Range: -8.5300
Max Act: 7.7175. Min Act: -0.1700
Data Index: 3791179 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5300. Min Range: -8.5300
Max Act: 7.6862. Min Act: -0.1700
Data Index: 1527270 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5300. Min Range: -8.5300
Max Act: 7.7175. Min Act: -0.1700
Data Index: 4042133 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5300. Min Range: -8.5300
Max Act: 7.6862. Min Act: -0.1700
Data Index: 6005462 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5300. Min Range: -8.5300
Max Act: 7.6550. Min Act: -0.1700
Data Index: 2544241 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19