Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 237 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.8551. Min Act: -0.1700
Data Index: 3531856 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.8551. Min Act: -0.1700
Data Index: 3180 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.8551. Min Act: -0.1700
Data Index: 1249326 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.8551. Min Act: -0.1700
Data Index: 5409969 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.8238. Min Act: -0.1700
Data Index: 2377455 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.7612. Min Act: -0.1700
Data Index: 8115512 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.6987. Min Act: -0.1700
Data Index: 8668909 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.6987. Min Act: -0.1700
Data Index: 3054433 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.6517. Min Act: -0.1700
Data Index: 5854228 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.6048. Min Act: -0.1700
Data Index: 4936435 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.6204. Min Act: -0.1700
Data Index: 3374703 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.5891. Min Act: -0.1700
Data Index: 925983 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.6048. Min Act: -0.1700
Data Index: 8570982 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.5891. Min Act: -0.1700
Data Index: 234153 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.6048. Min Act: -0.1700
Data Index: 6555006 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.5735. Min Act: -0.1700
Data Index: 7933309 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.5265. Min Act: -0.1700
Data Index: 1240946 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.5578. Min Act: -0.1700
Data Index: 3516694 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.5265. Min Act: -0.1700
Data Index: 1993441 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.5109. Min Act: -0.1700
Data Index: 2888292 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19