Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3770 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0749. Min Range: -5.0749
Max Act: 5.0749. Min Act: -0.1700
Data Index: 5769507 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0749. Min Range: -5.0749
Max Act: 5.0749. Min Act: -0.1700
Data Index: 3169243 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.8561. Min Act: -0.1700
Data Index: 5748767 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.8561. Min Act: -0.1700
Data Index: 4496214 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.8561. Min Act: -0.1700
Data Index: 1574468 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.8249. Min Act: -0.1700
Data Index: 5223282 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.8249. Min Act: -0.1700
Data Index: 8684869 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.8249. Min Act: -0.1700
Data Index: 5552499 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.8249. Min Act: -0.1700
Data Index: 159569 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.7936. Min Act: -0.1700
Data Index: 1616369 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.7624. Min Act: -0.1700
Data Index: 7750296 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.7936. Min Act: -0.1700
Data Index: 2368278 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.7936. Min Act: -0.1700
Data Index: 5306283 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.7936. Min Act: -0.1700
Data Index: 6123580 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.7936. Min Act: -0.1700
Data Index: 5934576 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.7624. Min Act: -0.1700
Data Index: 3494828 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.7624. Min Act: -0.1700
Data Index: 6166926 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.7624. Min Act: -0.1700
Data Index: 6766640 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.7311. Min Act: -0.1700
Data Index: 2648238 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.7936. Min Act: -0.1700
Data Index: 6084309 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19