Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5112 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0858. Min Range: -6.0858
Max Act: 6.0858. Min Act: -0.1700
Data Index: 2733336 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0858. Min Range: -6.0858
Max Act: 6.0233. Min Act: -0.1700
Data Index: 2414479 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0858. Min Range: -6.0858
Max Act: 6.0545. Min Act: -0.1700
Data Index: 3675555 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0858. Min Range: -6.0858
Max Act: 6.0545. Min Act: -0.1700
Data Index: 927615 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0858. Min Range: -6.0858
Max Act: 6.0545. Min Act: -0.1700
Data Index: 5937401 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0858. Min Range: -6.0858
Max Act: 6.0233. Min Act: -0.1700
Data Index: 4842624 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0858. Min Range: -6.0858
Max Act: 6.0233. Min Act: -0.1700
Data Index: 6017736 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.9920. Min Act: -0.1700
Data Index: 5190654 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.9608. Min Act: -0.1700
Data Index: 5600058 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.9608. Min Act: -0.1700
Data Index: 6424480 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.9295. Min Act: -0.1700
Data Index: 3859240 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.9295. Min Act: -0.1700
Data Index: 1511211 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.9295. Min Act: -0.1700
Data Index: 7194903 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.9295. Min Act: -0.1700
Data Index: 2257988 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.8983. Min Act: -0.1700
Data Index: 1525618 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.8983. Min Act: -0.1700
Data Index: 4220335 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.8983. Min Act: -0.1700
Data Index: 854566 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.8670. Min Act: -0.1700
Data Index: 1010752 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.8670. Min Act: -0.1700
Data Index: 6816474 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0858. Min Range: -6.0858
Max Act: 5.8045. Min Act: -0.1700
Data Index: 3047405 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19