Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1932 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4365. Min Range: -7.4365
Max Act: 7.4365. Min Act: -0.1700
Data Index: 2542000 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4365. Min Range: -7.4365
Max Act: 7.2177. Min Act: -0.1700
Data Index: 6853122 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4365. Min Range: -7.4365
Max Act: 7.1552. Min Act: -0.1700
Data Index: 8514257 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4365. Min Range: -7.4365
Max Act: 6.9990. Min Act: -0.1700
Data Index: 1016658 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4365. Min Range: -7.4365
Max Act: 6.9052. Min Act: -0.1700
Data Index: 6723190 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4365. Min Range: -7.4365
Max Act: 6.8740. Min Act: -0.1700
Data Index: 2209797 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4365. Min Range: -7.4365
Max Act: 6.8740. Min Act: -0.1700
Data Index: 122944 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4365. Min Range: -7.4365
Max Act: 6.8427. Min Act: -0.1700
Data Index: 360163 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4365. Min Range: -7.4365
Max Act: 6.8427. Min Act: -0.1700
Data Index: 6659650 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4365. Min Range: -7.4365
Max Act: 6.7802. Min Act: -0.1700
Data Index: 4816442 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4365. Min Range: -7.4365
Max Act: 6.7802. Min Act: -0.1700
Data Index: 46918 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4365. Min Range: -7.4365
Max Act: 6.8115. Min Act: -0.1700
Data Index: 2838809 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4365. Min Range: -7.4365
Max Act: 6.7490. Min Act: -0.1700
Data Index: 2521465 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4365. Min Range: -7.4365
Max Act: 6.7490. Min Act: -0.1700
Data Index: 6043160 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4365. Min Range: -7.4365
Max Act: 6.7177. Min Act: -0.1700
Data Index: 5856584 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4365. Min Range: -7.4365
Max Act: 6.6865. Min Act: -0.1700
Data Index: 6852129 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4365. Min Range: -7.4365
Max Act: 6.6865. Min Act: -0.1700
Data Index: 8509345 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4365. Min Range: -7.4365
Max Act: 6.6865. Min Act: -0.1700
Data Index: 2105204 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4365. Min Range: -7.4365
Max Act: 6.6240. Min Act: -0.1700
Data Index: 2519469 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4365. Min Range: -7.4365
Max Act: 6.6552. Min Act: -0.1700
Data Index: 2533454 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19