Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5387 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9846. Min Range: -7.9846
Max Act: 7.9846. Min Act: -0.1692
Data Index: 4900673 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9846. Min Range: -7.9846
Max Act: 7.9221. Min Act: -0.1700
Data Index: 8801326 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9846. Min Range: -7.9846
Max Act: 7.9534. Min Act: -0.1700
Data Index: 3869742 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9846. Min Range: -7.9846
Max Act: 7.9534. Min Act: -0.1700
Data Index: 2761974 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9846. Min Range: -7.9846
Max Act: 7.9534. Min Act: -0.1699
Data Index: 6745173 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9846. Min Range: -7.9846
Max Act: 7.8596. Min Act: -0.1700
Data Index: 3033466 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9846. Min Range: -7.9846
Max Act: 7.8284. Min Act: -0.1700
Data Index: 6354389 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9846. Min Range: -7.9846
Max Act: 7.8909. Min Act: -0.1700
Data Index: 7416694 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9846. Min Range: -7.9846
Max Act: 7.8284. Min Act: -0.1699
Data Index: 6498367 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9846. Min Range: -7.9846
Max Act: 7.8284. Min Act: -0.1700
Data Index: 3472295 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9846. Min Range: -7.9846
Max Act: 7.7659. Min Act: -0.1700
Data Index: 4799329 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9846. Min Range: -7.9846
Max Act: 7.7659. Min Act: -0.1693
Data Index: 5727971 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9846. Min Range: -7.9846
Max Act: 7.7034. Min Act: -0.1698
Data Index: 3266737 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9846. Min Range: -7.9846
Max Act: 7.6721. Min Act: -0.1698
Data Index: 1112125 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9846. Min Range: -7.9846
Max Act: 7.6721. Min Act: -0.1700
Data Index: 5444416 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9846. Min Range: -7.9846
Max Act: 7.6096. Min Act: -0.1700
Data Index: 4099917 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9846. Min Range: -7.9846
Max Act: 7.6096. Min Act: -0.1695
Data Index: 1735492 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9846. Min Range: -7.9846
Max Act: 7.5784. Min Act: -0.1700
Data Index: 6672694 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9846. Min Range: -7.9846
Max Act: 7.6096. Min Act: -0.1698
Data Index: 393368 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9846. Min Range: -7.9846
Max Act: 7.5784. Min Act: -0.1700
Data Index: 2667133 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19