Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2323 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4264. Min Range: -5.4264
Max Act: 5.4264. Min Act: -0.1700
Data Index: 4245992 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4264. Min Range: -5.4264
Max Act: 5.3639. Min Act: -0.1700
Data Index: 7189922 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4264. Min Range: -5.4264
Max Act: 5.3326. Min Act: -0.1700
Data Index: 489393 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4264. Min Range: -5.4264
Max Act: 5.1139. Min Act: -0.1700
Data Index: 4060775 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4264. Min Range: -5.4264
Max Act: 5.1139. Min Act: -0.1700
Data Index: 243596 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4264. Min Range: -5.4264
Max Act: 5.1139. Min Act: -0.1700
Data Index: 91055 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4264. Min Range: -5.4264
Max Act: 5.0514. Min Act: -0.1700
Data Index: 3856536 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4264. Min Range: -5.4264
Max Act: 5.0514. Min Act: -0.1700
Data Index: 1473672 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4264. Min Range: -5.4264
Max Act: 5.0514. Min Act: -0.1700
Data Index: 6901972 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4264. Min Range: -5.4264
Max Act: 5.0514. Min Act: -0.1700
Data Index: 5834751 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4264. Min Range: -5.4264
Max Act: 4.9889. Min Act: -0.1700
Data Index: 887065 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4264. Min Range: -5.4264
Max Act: 4.9889. Min Act: -0.1700
Data Index: 6539580 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4264. Min Range: -5.4264
Max Act: 4.9889. Min Act: -0.1700
Data Index: 385093 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4264. Min Range: -5.4264
Max Act: 4.9889. Min Act: -0.1700
Data Index: 2773157 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4264. Min Range: -5.4264
Max Act: 4.9576. Min Act: -0.1700
Data Index: 1608432 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4264. Min Range: -5.4264
Max Act: 4.9576. Min Act: -0.1700
Data Index: 2814226 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4264. Min Range: -5.4264
Max Act: 4.9264. Min Act: -0.1700
Data Index: 3121930 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4264. Min Range: -5.4264
Max Act: 4.9264. Min Act: -0.1700
Data Index: 5377164 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4264. Min Range: -5.4264
Max Act: 4.9264. Min Act: -0.1700
Data Index: 6748506 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4264. Min Range: -5.4264
Max Act: 4.8951. Min Act: -0.1700
Data Index: 5780617 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19