Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3518 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1019. Min Range: -7.1019
Max Act: 7.1019. Min Act: -0.1700
Data Index: 2662559 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1019. Min Range: -7.1019
Max Act: 7.0706. Min Act: -0.1700
Data Index: 8744054 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1019. Min Range: -7.1019
Max Act: 6.9456. Min Act: -0.1700
Data Index: 7430392 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1019. Min Range: -7.1019
Max Act: 6.6331. Min Act: -0.1700
Data Index: 4939398 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1019. Min Range: -7.1019
Max Act: 6.6644. Min Act: -0.1700
Data Index: 1526818 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1019. Min Range: -7.1019
Max Act: 6.6019. Min Act: -0.1700
Data Index: 7511522 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1019. Min Range: -7.1019
Max Act: 6.5394. Min Act: -0.1700
Data Index: 5687558 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1019. Min Range: -7.1019
Max Act: 6.4769. Min Act: -0.1700
Data Index: 6140763 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1019. Min Range: -7.1019
Max Act: 6.4769. Min Act: -0.1700
Data Index: 4519748 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1019. Min Range: -7.1019
Max Act: 6.4769. Min Act: -0.1700
Data Index: 1768633 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1019. Min Range: -7.1019
Max Act: 6.4769. Min Act: -0.1700
Data Index: 1823616 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1019. Min Range: -7.1019
Max Act: 6.4456. Min Act: -0.1700
Data Index: 700165 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1019. Min Range: -7.1019
Max Act: 6.4769. Min Act: -0.1700
Data Index: 6574317 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1019. Min Range: -7.1019
Max Act: 6.4144. Min Act: -0.1700
Data Index: 4402429 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1019. Min Range: -7.1019
Max Act: 6.4144. Min Act: -0.1700
Data Index: 119551 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1019. Min Range: -7.1019
Max Act: 6.3519. Min Act: -0.1700
Data Index: 1640122 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1019. Min Range: -7.1019
Max Act: 6.3831. Min Act: -0.1700
Data Index: 898458 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1019. Min Range: -7.1019
Max Act: 6.3831. Min Act: -0.1700
Data Index: 5807644 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1019. Min Range: -7.1019
Max Act: 6.3831. Min Act: -0.1700
Data Index: 2046202 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1019. Min Range: -7.1019
Max Act: 6.3206. Min Act: -0.1700
Data Index: 6200333 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19