Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2516 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4358. Min Range: -4.4358
Max Act: 4.4358. Min Act: -0.1700
Data Index: 3263856 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4358. Min Range: -4.4358
Max Act: 4.4046. Min Act: -0.1700
Data Index: 2579730 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4358. Min Range: -4.4358
Max Act: 4.3733. Min Act: -0.1700
Data Index: 2223639 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4358. Min Range: -4.4358
Max Act: 4.3733. Min Act: -0.1700
Data Index: 8130376 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4358. Min Range: -4.4358
Max Act: 4.3733. Min Act: -0.1700
Data Index: 1626260 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4358. Min Range: -4.4358
Max Act: 4.3733. Min Act: -0.1700
Data Index: 3000556 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4358. Min Range: -4.4358
Max Act: 4.3733. Min Act: -0.1700
Data Index: 7874982 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4358. Min Range: -4.4358
Max Act: 4.3733. Min Act: -0.1700
Data Index: 6540273 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4358. Min Range: -4.4358
Max Act: 4.3421. Min Act: -0.1700
Data Index: 5054615 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4358. Min Range: -4.4358
Max Act: 4.3421. Min Act: -0.1700
Data Index: 801797 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4358. Min Range: -4.4358
Max Act: 4.3421. Min Act: -0.1700
Data Index: 6674239 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4358. Min Range: -4.4358
Max Act: 4.3421. Min Act: -0.1700
Data Index: 713919 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4358. Min Range: -4.4358
Max Act: 4.3421. Min Act: -0.1700
Data Index: 5761012 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4358. Min Range: -4.4358
Max Act: 4.3421. Min Act: -0.1700
Data Index: 5635238 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4358. Min Range: -4.4358
Max Act: 4.3421. Min Act: -0.1700
Data Index: 3072886 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4358. Min Range: -4.4358
Max Act: 4.3421. Min Act: -0.1700
Data Index: 5576926 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4358. Min Range: -4.4358
Max Act: 4.3421. Min Act: -0.1700
Data Index: 2653799 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4358. Min Range: -4.4358
Max Act: 4.3421. Min Act: -0.1700
Data Index: 1065005 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4358. Min Range: -4.4358
Max Act: 4.3108. Min Act: -0.1700
Data Index: 3463725 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4358. Min Range: -4.4358
Max Act: 4.3108. Min Act: -0.1700
Data Index: 3619929 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19