Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2824 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0783. Min Range: -7.0783
Max Act: 7.0783. Min Act: -0.1700
Data Index: 1905901 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0783. Min Range: -7.0783
Max Act: 6.9846. Min Act: -0.1700
Data Index: 3613691 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0783. Min Range: -7.0783
Max Act: 6.9533. Min Act: -0.1700
Data Index: 5834830 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0783. Min Range: -7.0783
Max Act: 6.8908. Min Act: -0.1700
Data Index: 2633520 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0783. Min Range: -7.0783
Max Act: 6.7658. Min Act: -0.1700
Data Index: 1117258 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0783. Min Range: -7.0783
Max Act: 6.7033. Min Act: -0.1700
Data Index: 66850 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0783. Min Range: -7.0783
Max Act: 6.6721. Min Act: -0.1700
Data Index: 2506315 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0783. Min Range: -7.0783
Max Act: 6.6721. Min Act: -0.1700
Data Index: 77419 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0783. Min Range: -7.0783
Max Act: 6.6408. Min Act: -0.1700
Data Index: 113836 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0783. Min Range: -7.0783
Max Act: 6.6096. Min Act: -0.1700
Data Index: 3511921 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0783. Min Range: -7.0783
Max Act: 6.5783. Min Act: -0.1700
Data Index: 4249255 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0783. Min Range: -7.0783
Max Act: 6.5783. Min Act: -0.1700
Data Index: 1803351 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0783. Min Range: -7.0783
Max Act: 6.5783. Min Act: -0.1700
Data Index: 2967822 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0783. Min Range: -7.0783
Max Act: 6.5158. Min Act: -0.1700
Data Index: 6998299 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0783. Min Range: -7.0783
Max Act: 6.5158. Min Act: -0.1700
Data Index: 8148315 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0783. Min Range: -7.0783
Max Act: 6.5158. Min Act: -0.1700
Data Index: 1378548 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0783. Min Range: -7.0783
Max Act: 6.4846. Min Act: -0.1700
Data Index: 1340546 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0783. Min Range: -7.0783
Max Act: 6.4533. Min Act: -0.1700
Data Index: 2652640 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0783. Min Range: -7.0783
Max Act: 6.4533. Min Act: -0.1700
Data Index: 3632422 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0783. Min Range: -7.0783
Max Act: 6.4533. Min Act: -0.1700
Data Index: 6820749 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19