Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2697 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7013. Min Range: -9.7013
Max Act: 9.7013. Min Act: -0.1700
Data Index: 7197298 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7013. Min Range: -9.7013
Max Act: 9.7013. Min Act: -0.1700
Data Index: 6483023 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7013. Min Range: -9.7013
Max Act: 9.6388. Min Act: -0.1700
Data Index: 6863243 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7013. Min Range: -9.7013
Max Act: 9.4513. Min Act: -0.1700
Data Index: 5510474 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7013. Min Range: -9.7013
Max Act: 9.3888. Min Act: -0.1700
Data Index: 5136696 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7013. Min Range: -9.7013
Max Act: 9.2638. Min Act: -0.1700
Data Index: 5115348 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7013. Min Range: -9.7013
Max Act: 9.1388. Min Act: -0.1700
Data Index: 5734478 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7013. Min Range: -9.7013
Max Act: 9.0763. Min Act: -0.1700
Data Index: 7304700 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7013. Min Range: -9.7013
Max Act: 9.0763. Min Act: -0.1700
Data Index: 4873497 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7013. Min Range: -9.7013
Max Act: 9.0138. Min Act: -0.1700
Data Index: 121353 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7013. Min Range: -9.7013
Max Act: 9.0138. Min Act: -0.1700
Data Index: 6039696 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7013. Min Range: -9.7013
Max Act: 8.9513. Min Act: -0.1700
Data Index: 6084679 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7013. Min Range: -9.7013
Max Act: 8.8888. Min Act: -0.1700
Data Index: 4413523 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7013. Min Range: -9.7013
Max Act: 8.9513. Min Act: -0.1700
Data Index: 2975565 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7013. Min Range: -9.7013
Max Act: 8.8888. Min Act: -0.1700
Data Index: 3487879 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7013. Min Range: -9.7013
Max Act: 8.9513. Min Act: -0.1700
Data Index: 2840644 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7013. Min Range: -9.7013
Max Act: 8.9513. Min Act: -0.1700
Data Index: 703324 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7013. Min Range: -9.7013
Max Act: 8.8888. Min Act: -0.1700
Data Index: 6758156 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7013. Min Range: -9.7013
Max Act: 8.8888. Min Act: -0.1700
Data Index: 1080598 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7013. Min Range: -9.7013
Max Act: 8.8888. Min Act: -0.1700
Data Index: 4748281 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19