Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6333 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3536. Min Range: -7.3536
Max Act: 7.3536. Min Act: -0.1700
Data Index: 7854624 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3536. Min Range: -7.3536
Max Act: 7.2286. Min Act: -0.1700
Data Index: 3835316 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3536. Min Range: -7.3536
Max Act: 7.1974. Min Act: -0.1700
Data Index: 8637717 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3536. Min Range: -7.3536
Max Act: 7.0411. Min Act: -0.1700
Data Index: 6945959 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3536. Min Range: -7.3536
Max Act: 7.0724. Min Act: -0.1700
Data Index: 3105594 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3536. Min Range: -7.3536
Max Act: 6.9786. Min Act: -0.1700
Data Index: 8636157 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3536. Min Range: -7.3536
Max Act: 6.9786. Min Act: -0.1700
Data Index: 1343583 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3536. Min Range: -7.3536
Max Act: 6.9161. Min Act: -0.1700
Data Index: 1287491 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3536. Min Range: -7.3536
Max Act: 6.9161. Min Act: -0.1700
Data Index: 115837 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3536. Min Range: -7.3536
Max Act: 6.8849. Min Act: -0.1700
Data Index: 5332025 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3536. Min Range: -7.3536
Max Act: 6.8849. Min Act: -0.1700
Data Index: 5448921 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3536. Min Range: -7.3536
Max Act: 6.8536. Min Act: -0.1700
Data Index: 2494539 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3536. Min Range: -7.3536
Max Act: 6.8536. Min Act: -0.1700
Data Index: 5635322 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3536. Min Range: -7.3536
Max Act: 6.8224. Min Act: -0.1700
Data Index: 1964072 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3536. Min Range: -7.3536
Max Act: 6.8224. Min Act: -0.1700
Data Index: 5047794 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3536. Min Range: -7.3536
Max Act: 6.7911. Min Act: -0.1700
Data Index: 4407505 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3536. Min Range: -7.3536
Max Act: 6.7911. Min Act: -0.1700
Data Index: 4114677 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3536. Min Range: -7.3536
Max Act: 6.7911. Min Act: -0.1700
Data Index: 2726541 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3536. Min Range: -7.3536
Max Act: 6.7911. Min Act: -0.1700
Data Index: 5824484 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3536. Min Range: -7.3536
Max Act: 6.7911. Min Act: -0.1700
Data Index: 2488169 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19