Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 59 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9330. Min Range: -4.9330
Max Act: 4.9330. Min Act: -0.1700
Data Index: 3797560 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9330. Min Range: -4.9330
Max Act: 4.9330. Min Act: -0.1700
Data Index: 7001600 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9330. Min Range: -4.9330
Max Act: 4.9018. Min Act: -0.1700
Data Index: 4539341 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9330. Min Range: -4.9330
Max Act: 4.8393. Min Act: -0.1700
Data Index: 1059409 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9330. Min Range: -4.9330
Max Act: 4.8080. Min Act: -0.1700
Data Index: 5323132 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9330. Min Range: -4.9330
Max Act: 4.8080. Min Act: -0.1700
Data Index: 5211954 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9330. Min Range: -4.9330
Max Act: 4.8080. Min Act: -0.1700
Data Index: 5036294 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9330. Min Range: -4.9330
Max Act: 4.7768. Min Act: -0.1700
Data Index: 459573 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9330. Min Range: -4.9330
Max Act: 4.7768. Min Act: -0.1700
Data Index: 2938871 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9330. Min Range: -4.9330
Max Act: 4.7455. Min Act: -0.1700
Data Index: 7714880 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9330. Min Range: -4.9330
Max Act: 4.7455. Min Act: -0.1700
Data Index: 4558380 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9330. Min Range: -4.9330
Max Act: 4.7455. Min Act: -0.1700
Data Index: 5313256 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9330. Min Range: -4.9330
Max Act: 4.7455. Min Act: -0.1700
Data Index: 2777204 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9330. Min Range: -4.9330
Max Act: 4.7455. Min Act: -0.1700
Data Index: 1736989 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9330. Min Range: -4.9330
Max Act: 4.7455. Min Act: -0.1700
Data Index: 6817868 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9330. Min Range: -4.9330
Max Act: 4.7455. Min Act: -0.1700
Data Index: 2746246 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9330. Min Range: -4.9330
Max Act: 4.7455. Min Act: -0.1700
Data Index: 6403789 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9330. Min Range: -4.9330
Max Act: 4.7455. Min Act: -0.1700
Data Index: 5250096 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9330. Min Range: -4.9330
Max Act: 4.6830. Min Act: -0.1700
Data Index: 2716125 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9330. Min Range: -4.9330
Max Act: 4.7455. Min Act: -0.1700
Data Index: 910186 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19