Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1987 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6021. Min Range: -8.6021
Max Act: 8.6021. Min Act: -0.1700
Data Index: 4348686 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6021. Min Range: -8.6021
Max Act: 8.4771. Min Act: -0.1700
Data Index: 8333057 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6021. Min Range: -8.6021
Max Act: 8.2896. Min Act: -0.1700
Data Index: 1479196 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6021. Min Range: -8.6021
Max Act: 8.2896. Min Act: -0.1700
Data Index: 4325481 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6021. Min Range: -8.6021
Max Act: 8.3521. Min Act: -0.1700
Data Index: 7851684 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6021. Min Range: -8.6021
Max Act: 8.2271. Min Act: -0.1700
Data Index: 585674 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6021. Min Range: -8.6021
Max Act: 8.2271. Min Act: -0.1700
Data Index: 691824 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6021. Min Range: -8.6021
Max Act: 8.1646. Min Act: -0.1700
Data Index: 6556447 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6021. Min Range: -8.6021
Max Act: 8.1021. Min Act: -0.1700
Data Index: 4660178 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6021. Min Range: -8.6021
Max Act: 8.1021. Min Act: -0.1700
Data Index: 5872562 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6021. Min Range: -8.6021
Max Act: 8.1021. Min Act: -0.1700
Data Index: 717465 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6021. Min Range: -8.6021
Max Act: 8.1021. Min Act: -0.1700
Data Index: 1024456 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6021. Min Range: -8.6021
Max Act: 8.0396. Min Act: -0.1700
Data Index: 8126878 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6021. Min Range: -8.6021
Max Act: 8.0396. Min Act: -0.1700
Data Index: 900091 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6021. Min Range: -8.6021
Max Act: 8.0396. Min Act: -0.1700
Data Index: 4118627 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6021. Min Range: -8.6021
Max Act: 8.0396. Min Act: -0.1700
Data Index: 7775751 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6021. Min Range: -8.6021
Max Act: 7.9771. Min Act: -0.1700
Data Index: 1693245 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6021. Min Range: -8.6021
Max Act: 7.9771. Min Act: -0.1700
Data Index: 1287941 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6021. Min Range: -8.6021
Max Act: 7.9771. Min Act: -0.1700
Data Index: 2063625 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6021. Min Range: -8.6021
Max Act: 7.9771. Min Act: -0.1700
Data Index: 182309 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19