Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3508 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2537. Min Range: -5.2537
Max Act: 5.2537. Min Act: -0.1700
Data Index: 290850 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2537. Min Range: -5.2537
Max Act: 4.9724. Min Act: -0.1700
Data Index: 2261677 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2537. Min Range: -5.2537
Max Act: 4.9412. Min Act: -0.1700
Data Index: 6689026 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2537. Min Range: -5.2537
Max Act: 4.9412. Min Act: -0.1700
Data Index: 5866723 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2537. Min Range: -5.2537
Max Act: 4.9412. Min Act: -0.1700
Data Index: 3170352 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2537. Min Range: -5.2537
Max Act: 4.9099. Min Act: -0.1700
Data Index: 6954301 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2537. Min Range: -5.2537
Max Act: 4.9099. Min Act: -0.1700
Data Index: 4650700 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2537. Min Range: -5.2537
Max Act: 4.8787. Min Act: -0.1700
Data Index: 4840615 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2537. Min Range: -5.2537
Max Act: 4.8787. Min Act: -0.1700
Data Index: 5253437 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2537. Min Range: -5.2537
Max Act: 4.8787. Min Act: -0.1700
Data Index: 967340 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2537. Min Range: -5.2537
Max Act: 4.9099. Min Act: -0.1700
Data Index: 4005257 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2537. Min Range: -5.2537
Max Act: 4.8787. Min Act: -0.1700
Data Index: 5666692 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2537. Min Range: -5.2537
Max Act: 4.8787. Min Act: -0.1700
Data Index: 3502280 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2537. Min Range: -5.2537
Max Act: 4.9099. Min Act: -0.1700
Data Index: 5804174 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2537. Min Range: -5.2537
Max Act: 4.8787. Min Act: -0.1700
Data Index: 6038651 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2537. Min Range: -5.2537
Max Act: 4.8474. Min Act: -0.1700
Data Index: 2232053 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2537. Min Range: -5.2537
Max Act: 4.8474. Min Act: -0.1700
Data Index: 3819172 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2537. Min Range: -5.2537
Max Act: 4.8474. Min Act: -0.1700
Data Index: 3043730 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2537. Min Range: -5.2537
Max Act: 4.8162. Min Act: -0.1700
Data Index: 4485151 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2537. Min Range: -5.2537
Max Act: 4.8474. Min Act: -0.1700
Data Index: 3545813 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19