Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3629 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4384. Min Range: -3.4384
Max Act: 3.4384. Min Act: -0.1700
Data Index: 6831281 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4384. Min Range: -3.4384
Max Act: 3.3443. Min Act: -0.1700
Data Index: 2253851 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4384. Min Range: -3.4384
Max Act: 3.3129. Min Act: -0.1700
Data Index: 629540 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4384. Min Range: -3.4384
Max Act: 3.3129. Min Act: -0.1700
Data Index: 629542 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4384. Min Range: -3.4384
Max Act: 3.3129. Min Act: -0.1700
Data Index: 5707895 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4384. Min Range: -3.4384
Max Act: 3.3129. Min Act: -0.1700
Data Index: 6565423 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4384. Min Range: -3.4384
Max Act: 3.2815. Min Act: -0.1700
Data Index: 2382678 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4384. Min Range: -3.4384
Max Act: 3.2815. Min Act: -0.1700
Data Index: 8586797 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4384. Min Range: -3.4384
Max Act: 3.2815. Min Act: -0.1700
Data Index: 3444553 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4384. Min Range: -3.4384
Max Act: 3.2501. Min Act: -0.1700
Data Index: 1700278 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4384. Min Range: -3.4384
Max Act: 3.2187. Min Act: -0.1700
Data Index: 8720144 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4384. Min Range: -3.4384
Max Act: 3.2187. Min Act: -0.1700
Data Index: 4167443 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4384. Min Range: -3.4384
Max Act: 3.2187. Min Act: -0.1700
Data Index: 2186275 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4384. Min Range: -3.4384
Max Act: 3.2187. Min Act: -0.1700
Data Index: 4607199 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4384. Min Range: -3.4384
Max Act: 3.1872. Min Act: -0.1700
Data Index: 8013333 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4384. Min Range: -3.4384
Max Act: 3.1872. Min Act: -0.1700
Data Index: 5500024 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4384. Min Range: -3.4384
Max Act: 3.1872. Min Act: -0.1700
Data Index: 629541 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4384. Min Range: -3.4384
Max Act: 3.1558. Min Act: -0.1700
Data Index: 64769 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4384. Min Range: -3.4384
Max Act: 3.1558. Min Act: -0.1700
Data Index: 6835455 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4384. Min Range: -3.4384
Max Act: 3.1558. Min Act: -0.1700
Data Index: 4771543 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19