Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2066 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5386. Min Range: -5.5386
Max Act: 5.5386. Min Act: -0.1700
Data Index: 2535684 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5386. Min Range: -5.5386
Max Act: 5.5386. Min Act: -0.1700
Data Index: 4574691 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5386. Min Range: -5.5386
Max Act: 5.5386. Min Act: -0.1700
Data Index: 2907349 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5386. Min Range: -5.5386
Max Act: 5.4761. Min Act: -0.1700
Data Index: 420677 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5386. Min Range: -5.5386
Max Act: 5.3199. Min Act: -0.1700
Data Index: 3733887 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5386. Min Range: -5.5386
Max Act: 5.2574. Min Act: -0.1700
Data Index: 7149191 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5386. Min Range: -5.5386
Max Act: 5.2574. Min Act: -0.1700
Data Index: 1772990 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5386. Min Range: -5.5386
Max Act: 5.1636. Min Act: -0.1700
Data Index: 630385 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5386. Min Range: -5.5386
Max Act: 5.1636. Min Act: -0.1700
Data Index: 2440943 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5386. Min Range: -5.5386
Max Act: 5.1011. Min Act: -0.1700
Data Index: 7530496 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5386. Min Range: -5.5386
Max Act: 5.0699. Min Act: -0.1700
Data Index: 2930970 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5386. Min Range: -5.5386
Max Act: 5.0386. Min Act: -0.1700
Data Index: 4596865 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5386. Min Range: -5.5386
Max Act: 5.0386. Min Act: -0.1700
Data Index: 8625442 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5386. Min Range: -5.5386
Max Act: 5.0074. Min Act: -0.1700
Data Index: 110302 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5386. Min Range: -5.5386
Max Act: 4.9761. Min Act: -0.1700
Data Index: 5442068 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5386. Min Range: -5.5386
Max Act: 5.0074. Min Act: -0.1700
Data Index: 6423000 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5386. Min Range: -5.5386
Max Act: 4.9761. Min Act: -0.1700
Data Index: 3518495 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5386. Min Range: -5.5386
Max Act: 4.9449. Min Act: -0.1700
Data Index: 1211008 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5386. Min Range: -5.5386
Max Act: 4.9449. Min Act: -0.1700
Data Index: 6173753 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5386. Min Range: -5.5386
Max Act: 4.9449. Min Act: -0.1700
Data Index: 2594381 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19