Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1761 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4554. Min Range: -6.4554
Max Act: 6.4554. Min Act: -0.1700
Data Index: 1632156 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4554. Min Range: -6.4554
Max Act: 6.3304. Min Act: -0.1700
Data Index: 267295 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4554. Min Range: -6.4554
Max Act: 6.2992. Min Act: -0.1700
Data Index: 8087682 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4554. Min Range: -6.4554
Max Act: 6.2679. Min Act: -0.1700
Data Index: 3750201 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4554. Min Range: -6.4554
Max Act: 6.2367. Min Act: -0.1700
Data Index: 7396717 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4554. Min Range: -6.4554
Max Act: 6.2679. Min Act: -0.1700
Data Index: 4253376 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4554. Min Range: -6.4554
Max Act: 6.1742. Min Act: -0.1700
Data Index: 7038744 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4554. Min Range: -6.4554
Max Act: 6.1429. Min Act: -0.1700
Data Index: 458102 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4554. Min Range: -6.4554
Max Act: 6.1117. Min Act: -0.1700
Data Index: 8577254 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4554. Min Range: -6.4554
Max Act: 6.0804. Min Act: -0.1700
Data Index: 6696552 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4554. Min Range: -6.4554
Max Act: 6.0804. Min Act: -0.1700
Data Index: 2531432 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4554. Min Range: -6.4554
Max Act: 6.0804. Min Act: -0.1700
Data Index: 685451 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4554. Min Range: -6.4554
Max Act: 6.0804. Min Act: -0.1700
Data Index: 5656839 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4554. Min Range: -6.4554
Max Act: 6.0492. Min Act: -0.1700
Data Index: 1439543 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4554. Min Range: -6.4554
Max Act: 6.0492. Min Act: -0.1700
Data Index: 68869 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4554. Min Range: -6.4554
Max Act: 6.0179. Min Act: -0.1700
Data Index: 796657 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4554. Min Range: -6.4554
Max Act: 5.9554. Min Act: -0.1700
Data Index: 785628 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4554. Min Range: -6.4554
Max Act: 5.9554. Min Act: -0.1700
Data Index: 7924409 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4554. Min Range: -6.4554
Max Act: 5.8929. Min Act: -0.1700
Data Index: 2410000 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4554. Min Range: -6.4554
Max Act: 5.9242. Min Act: -0.1700
Data Index: 5051679 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19