Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5403 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3588. Min Range: -6.3588
Max Act: 6.3588. Min Act: -0.1700
Data Index: 8631109 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3588. Min Range: -6.3588
Max Act: 6.2338. Min Act: -0.1700
Data Index: 6654189 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3588. Min Range: -6.3588
Max Act: 6.0776. Min Act: -0.1700
Data Index: 2324736 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3588. Min Range: -6.3588
Max Act: 5.9838. Min Act: -0.1700
Data Index: 7389808 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3588. Min Range: -6.3588
Max Act: 5.9213. Min Act: -0.1700
Data Index: 1283920 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3588. Min Range: -6.3588
Max Act: 5.8588. Min Act: -0.1700
Data Index: 4265910 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3588. Min Range: -6.3588
Max Act: 5.7963. Min Act: -0.1700
Data Index: 1249213 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3588. Min Range: -6.3588
Max Act: 5.7963. Min Act: -0.1700
Data Index: 4956941 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3588. Min Range: -6.3588
Max Act: 5.7963. Min Act: -0.1700
Data Index: 1530296 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3588. Min Range: -6.3588
Max Act: 5.7651. Min Act: -0.1700
Data Index: 8411934 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3588. Min Range: -6.3588
Max Act: 5.7026. Min Act: -0.1700
Data Index: 3525327 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3588. Min Range: -6.3588
Max Act: 5.7026. Min Act: -0.1700
Data Index: 6501671 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3588. Min Range: -6.3588
Max Act: 5.7026. Min Act: -0.1700
Data Index: 5434303 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3588. Min Range: -6.3588
Max Act: 5.7026. Min Act: -0.1700
Data Index: 1452367 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3588. Min Range: -6.3588
Max Act: 5.7026. Min Act: -0.1700
Data Index: 6653102 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3588. Min Range: -6.3588
Max Act: 5.7026. Min Act: -0.1700
Data Index: 5393299 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3588. Min Range: -6.3588
Max Act: 5.6401. Min Act: -0.1700
Data Index: 6353409 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3588. Min Range: -6.3588
Max Act: 5.6401. Min Act: -0.1700
Data Index: 1817932 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3588. Min Range: -6.3588
Max Act: 5.5776. Min Act: -0.1700
Data Index: 524414 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3588. Min Range: -6.3588
Max Act: 5.6088. Min Act: -0.1700
Data Index: 7300480 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19