Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4504 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9541. Min Range: -3.9541
Max Act: 3.9541. Min Act: -0.1700
Data Index: 7289816 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9541. Min Range: -3.9541
Max Act: 3.7821. Min Act: -0.1700
Data Index: 1364311 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9541. Min Range: -3.9541
Max Act: 3.7039. Min Act: -0.1700
Data Index: 5403669 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9541. Min Range: -3.9541
Max Act: 3.7039. Min Act: -0.1700
Data Index: 5286860 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9541. Min Range: -3.9541
Max Act: 3.7195. Min Act: -0.1700
Data Index: 6628306 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9541. Min Range: -3.9541
Max Act: 3.6882. Min Act: -0.1700
Data Index: 6865842 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9541. Min Range: -3.9541
Max Act: 3.6726. Min Act: -0.1700
Data Index: 2525792 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9541. Min Range: -3.9541
Max Act: 3.6569. Min Act: -0.1700
Data Index: 2673125 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9541. Min Range: -3.9541
Max Act: 3.6726. Min Act: -0.1700
Data Index: 938717 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9541. Min Range: -3.9541
Max Act: 3.6413. Min Act: -0.1700
Data Index: 8341987 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9541. Min Range: -3.9541
Max Act: 3.6256. Min Act: -0.1700
Data Index: 1712904 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9541. Min Range: -3.9541
Max Act: 3.6413. Min Act: -0.1700
Data Index: 7741758 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9541. Min Range: -3.9541
Max Act: 3.6256. Min Act: -0.1700
Data Index: 845649 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9541. Min Range: -3.9541
Max Act: 3.6256. Min Act: -0.1700
Data Index: 7084577 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9541. Min Range: -3.9541
Max Act: 3.6100. Min Act: -0.1700
Data Index: 4490125 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9541. Min Range: -3.9541
Max Act: 3.6100. Min Act: -0.1700
Data Index: 1324079 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9541. Min Range: -3.9541
Max Act: 3.6100. Min Act: -0.1700
Data Index: 6815739 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9541. Min Range: -3.9541
Max Act: 3.6100. Min Act: -0.1700
Data Index: 5333395 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9541. Min Range: -3.9541
Max Act: 3.5943. Min Act: -0.1700
Data Index: 4300236 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9541. Min Range: -3.9541
Max Act: 3.6100. Min Act: -0.1700
Data Index: 2855094 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19