Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3133 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9390. Min Range: -7.9390
Max Act: 7.9390. Min Act: -0.1700
Data Index: 6655884 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9390. Min Range: -7.9390
Max Act: 7.8765. Min Act: -0.1700
Data Index: 1466857 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9390. Min Range: -7.9390
Max Act: 7.8140. Min Act: -0.1700
Data Index: 2870321 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9390. Min Range: -7.9390
Max Act: 7.7515. Min Act: -0.1700
Data Index: 914772 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9390. Min Range: -7.9390
Max Act: 7.7515. Min Act: -0.1700
Data Index: 8486416 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9390. Min Range: -7.9390
Max Act: 7.6890. Min Act: -0.1700
Data Index: 8334681 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9390. Min Range: -7.9390
Max Act: 7.6890. Min Act: -0.1700
Data Index: 1946550 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9390. Min Range: -7.9390
Max Act: 7.6890. Min Act: -0.1700
Data Index: 6253103 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9390. Min Range: -7.9390
Max Act: 7.6890. Min Act: -0.1700
Data Index: 1512110 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9390. Min Range: -7.9390
Max Act: 7.6265. Min Act: -0.1700
Data Index: 4818473 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9390. Min Range: -7.9390
Max Act: 7.5640. Min Act: -0.1700
Data Index: 8135335 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9390. Min Range: -7.9390
Max Act: 7.5640. Min Act: -0.1700
Data Index: 5905619 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9390. Min Range: -7.9390
Max Act: 7.5015. Min Act: -0.1700
Data Index: 1571922 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9390. Min Range: -7.9390
Max Act: 7.4703. Min Act: -0.1700
Data Index: 3768718 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9390. Min Range: -7.9390
Max Act: 7.4703. Min Act: -0.1700
Data Index: 3983394 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9390. Min Range: -7.9390
Max Act: 7.5015. Min Act: -0.1700
Data Index: 8639771 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9390. Min Range: -7.9390
Max Act: 7.4703. Min Act: -0.1700
Data Index: 5264652 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9390. Min Range: -7.9390
Max Act: 7.4390. Min Act: -0.1700
Data Index: 2389702 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9390. Min Range: -7.9390
Max Act: 7.4390. Min Act: -0.1700
Data Index: 3561305 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9390. Min Range: -7.9390
Max Act: 7.4078. Min Act: -0.1700
Data Index: 3042586 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19