Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5123 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3585. Min Range: -5.3585
Max Act: 5.3585. Min Act: -0.1700
Data Index: 5683792 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3585. Min Range: -5.3585
Max Act: 5.2335. Min Act: -0.1700
Data Index: 4973176 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3585. Min Range: -5.3585
Max Act: 5.2023. Min Act: -0.1700
Data Index: 8071745 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3585. Min Range: -5.3585
Max Act: 5.1710. Min Act: -0.1700
Data Index: 5613495 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3585. Min Range: -5.3585
Max Act: 5.1398. Min Act: -0.1700
Data Index: 475756 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3585. Min Range: -5.3585
Max Act: 5.1398. Min Act: -0.1700
Data Index: 5649827 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3585. Min Range: -5.3585
Max Act: 5.1398. Min Act: -0.1700
Data Index: 4743962 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3585. Min Range: -5.3585
Max Act: 5.1398. Min Act: -0.1700
Data Index: 8095558 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3585. Min Range: -5.3585
Max Act: 5.1085. Min Act: -0.1700
Data Index: 356254 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3585. Min Range: -5.3585
Max Act: 5.0773. Min Act: -0.1700
Data Index: 376711 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3585. Min Range: -5.3585
Max Act: 5.0773. Min Act: -0.1700
Data Index: 2637811 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3585. Min Range: -5.3585
Max Act: 5.0773. Min Act: -0.1700
Data Index: 1274686 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3585. Min Range: -5.3585
Max Act: 5.0460. Min Act: -0.1700
Data Index: 863573 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3585. Min Range: -5.3585
Max Act: 5.0460. Min Act: -0.1700
Data Index: 542531 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3585. Min Range: -5.3585
Max Act: 5.0460. Min Act: -0.1700
Data Index: 196553 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3585. Min Range: -5.3585
Max Act: 4.9835. Min Act: -0.1700
Data Index: 3382689 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3585. Min Range: -5.3585
Max Act: 4.9835. Min Act: -0.1700
Data Index: 320097 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3585. Min Range: -5.3585
Max Act: 5.0148. Min Act: -0.1700
Data Index: 6315935 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3585. Min Range: -5.3585
Max Act: 5.0148. Min Act: -0.1700
Data Index: 4903315 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3585. Min Range: -5.3585
Max Act: 4.9835. Min Act: -0.1700
Data Index: 2151537 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #19