Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2037 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2378. Min Range: -3.2378
Max Act: 3.2378. Min Act: -0.1700
Data Index: 1132916 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2378. Min Range: -3.2378
Max Act: 3.1906. Min Act: -0.1700
Data Index: 1200209 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2378. Min Range: -3.2378
Max Act: 3.1749. Min Act: -0.1700
Data Index: 4039425 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2378. Min Range: -3.2378
Max Act: 3.1277. Min Act: -0.1700
Data Index: 6736390 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2378. Min Range: -3.2378
Max Act: 3.1277. Min Act: -0.1700
Data Index: 3525663 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2378. Min Range: -3.2378
Max Act: 3.0646. Min Act: -0.1700
Data Index: 3707467 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2378. Min Range: -3.2378
Max Act: 3.0962. Min Act: -0.1700
Data Index: 1452777 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2378. Min Range: -3.2378
Max Act: 3.0962. Min Act: -0.1700
Data Index: 6736389 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2378. Min Range: -3.2378
Max Act: 3.0646. Min Act: -0.1700
Data Index: 3310974 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2378. Min Range: -3.2378
Max Act: 3.0962. Min Act: -0.1700
Data Index: 4864344 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2378. Min Range: -3.2378
Max Act: 3.0646. Min Act: -0.1700
Data Index: 8095259 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2378. Min Range: -3.2378
Max Act: 3.0488. Min Act: -0.1700
Data Index: 6733563 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2378. Min Range: -3.2378
Max Act: 3.0488. Min Act: -0.1700
Data Index: 3030137 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2378. Min Range: -3.2378
Max Act: 3.0331. Min Act: -0.1700
Data Index: 8320659 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2378. Min Range: -3.2378
Max Act: 3.0488. Min Act: -0.1700
Data Index: 6908765 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2378. Min Range: -3.2378
Max Act: 3.0488. Min Act: -0.1700
Data Index: 4972014 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2378. Min Range: -3.2378
Max Act: 3.0646. Min Act: -0.1700
Data Index: 1622158 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2378. Min Range: -3.2378
Max Act: 3.0646. Min Act: -0.1700
Data Index: 7210584 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2378. Min Range: -3.2378
Max Act: 2.9857. Min Act: -0.1700
Data Index: 876314 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2378. Min Range: -3.2378
Max Act: 3.0488. Min Act: -0.1700
Data Index: 484944 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19