Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2107 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4078. Min Range: -5.4078
Max Act: 5.4078. Min Act: -0.1700
Data Index: 8509898 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4078. Min Range: -5.4078
Max Act: 5.2828. Min Act: -0.1700
Data Index: 3673281 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4078. Min Range: -5.4078
Max Act: 5.0640. Min Act: -0.1700
Data Index: 2261782 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4078. Min Range: -5.4078
Max Act: 5.0640. Min Act: -0.1700
Data Index: 2848657 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4078. Min Range: -5.4078
Max Act: 5.0328. Min Act: -0.1700
Data Index: 270109 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4078. Min Range: -5.4078
Max Act: 5.0015. Min Act: -0.1700
Data Index: 8509899 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4078. Min Range: -5.4078
Max Act: 5.0015. Min Act: -0.1700
Data Index: 5583383 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4078. Min Range: -5.4078
Max Act: 4.9390. Min Act: -0.1700
Data Index: 1080471 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4078. Min Range: -5.4078
Max Act: 4.9078. Min Act: -0.1700
Data Index: 5137515 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4078. Min Range: -5.4078
Max Act: 4.8765. Min Act: -0.1700
Data Index: 2155986 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4078. Min Range: -5.4078
Max Act: 4.8765. Min Act: -0.1700
Data Index: 8667072 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4078. Min Range: -5.4078
Max Act: 4.8453. Min Act: -0.1700
Data Index: 4536784 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4078. Min Range: -5.4078
Max Act: 4.7828. Min Act: -0.1700
Data Index: 8218151 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4078. Min Range: -5.4078
Max Act: 4.7828. Min Act: -0.1700
Data Index: 2440380 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4078. Min Range: -5.4078
Max Act: 4.7515. Min Act: -0.1700
Data Index: 8509897 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4078. Min Range: -5.4078
Max Act: 4.7515. Min Act: -0.1700
Data Index: 1911319 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4078. Min Range: -5.4078
Max Act: 4.7515. Min Act: -0.1700
Data Index: 3641500 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4078. Min Range: -5.4078
Max Act: 4.7515. Min Act: -0.1700
Data Index: 5018666 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4078. Min Range: -5.4078
Max Act: 4.7203. Min Act: -0.1700
Data Index: 2838312 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4078. Min Range: -5.4078
Max Act: 4.7203. Min Act: -0.1700
Data Index: 3545524 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19