Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4109 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2220. Min Range: -8.2220
Max Act: 8.2220. Min Act: -0.1700
Data Index: 6724825 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2220. Min Range: -8.2220
Max Act: 7.9720. Min Act: -0.1700
Data Index: 7164623 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2220. Min Range: -8.2220
Max Act: 7.9720. Min Act: -0.1700
Data Index: 4300670 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2220. Min Range: -8.2220
Max Act: 7.8470. Min Act: -0.1700
Data Index: 1305826 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2220. Min Range: -8.2220
Max Act: 7.9095. Min Act: -0.1700
Data Index: 6468701 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2220. Min Range: -8.2220
Max Act: 7.8470. Min Act: -0.1700
Data Index: 8798395 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2220. Min Range: -8.2220
Max Act: 7.8470. Min Act: -0.1700
Data Index: 549421 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2220. Min Range: -8.2220
Max Act: 7.7845. Min Act: -0.1700
Data Index: 7776998 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2220. Min Range: -8.2220
Max Act: 7.7845. Min Act: -0.1700
Data Index: 5968565 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2220. Min Range: -8.2220
Max Act: 7.7220. Min Act: -0.1700
Data Index: 8453553 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2220. Min Range: -8.2220
Max Act: 7.7220. Min Act: -0.1700
Data Index: 2087379 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2220. Min Range: -8.2220
Max Act: 7.7220. Min Act: -0.1700
Data Index: 4513838 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2220. Min Range: -8.2220
Max Act: 7.6595. Min Act: -0.1700
Data Index: 4611766 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2220. Min Range: -8.2220
Max Act: 7.5970. Min Act: -0.1700
Data Index: 6960333 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2220. Min Range: -8.2220
Max Act: 7.6595. Min Act: -0.1700
Data Index: 2283124 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2220. Min Range: -8.2220
Max Act: 7.6595. Min Act: -0.1700
Data Index: 4374282 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2220. Min Range: -8.2220
Max Act: 7.6595. Min Act: -0.1700
Data Index: 1850634 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2220. Min Range: -8.2220
Max Act: 7.5345. Min Act: -0.1700
Data Index: 874958 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2220. Min Range: -8.2220
Max Act: 7.5970. Min Act: -0.1700
Data Index: 682112 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2220. Min Range: -8.2220
Max Act: 7.5345. Min Act: -0.1700
Data Index: 3542504 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19