Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4706 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1094. Min Range: -6.1094
Max Act: 6.1094. Min Act: -0.1700
Data Index: 4729773 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1094. Min Range: -6.1094
Max Act: 5.3282. Min Act: -0.1700
Data Index: 1097493 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1094. Min Range: -6.1094
Max Act: 5.2657. Min Act: -0.1700
Data Index: 99131 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1094. Min Range: -6.1094
Max Act: 5.2657. Min Act: -0.1700
Data Index: 3813501 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1094. Min Range: -6.1094
Max Act: 5.2032. Min Act: -0.1700
Data Index: 8389518 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1094. Min Range: -6.1094
Max Act: 5.2344. Min Act: -0.1700
Data Index: 2586695 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1094. Min Range: -6.1094
Max Act: 5.2032. Min Act: -0.1700
Data Index: 3262875 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1094. Min Range: -6.1094
Max Act: 5.1719. Min Act: -0.1700
Data Index: 4625503 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1094. Min Range: -6.1094
Max Act: 5.1719. Min Act: -0.1700
Data Index: 8660435 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1094. Min Range: -6.1094
Max Act: 5.1094. Min Act: -0.1700
Data Index: 6083456 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1094. Min Range: -6.1094
Max Act: 5.1719. Min Act: -0.1700
Data Index: 7347747 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1094. Min Range: -6.1094
Max Act: 5.1094. Min Act: -0.1700
Data Index: 4454316 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1094. Min Range: -6.1094
Max Act: 5.1094. Min Act: -0.1700
Data Index: 7501119 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1094. Min Range: -6.1094
Max Act: 5.1094. Min Act: -0.1700
Data Index: 1746030 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1094. Min Range: -6.1094
Max Act: 5.1094. Min Act: -0.1700
Data Index: 3832348 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1094. Min Range: -6.1094
Max Act: 5.0469. Min Act: -0.1700
Data Index: 3823329 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1094. Min Range: -6.1094
Max Act: 5.0782. Min Act: -0.1700
Data Index: 4109738 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1094. Min Range: -6.1094
Max Act: 5.0782. Min Act: -0.1700
Data Index: 6559112 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1094. Min Range: -6.1094
Max Act: 5.0782. Min Act: -0.1700
Data Index: 2917935 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1094. Min Range: -6.1094
Max Act: 5.0782. Min Act: -0.1700
Data Index: 8612476 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19