Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1921 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.4905. Min Act: -0.1700
Data Index: 969522 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.2405. Min Act: -0.1700
Data Index: 3763609 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.2405. Min Act: -0.1700
Data Index: 8189585 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.1780. Min Act: -0.1700
Data Index: 388210 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.1155. Min Act: -0.1700
Data Index: 7269227 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.0843. Min Act: -0.1700
Data Index: 8332388 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4905. Min Range: -7.4905
Max Act: 6.9280. Min Act: -0.1700
Data Index: 7511128 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4905. Min Range: -7.4905
Max Act: 6.9280. Min Act: -0.1700
Data Index: 7553653 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4905. Min Range: -7.4905
Max Act: 6.8655. Min Act: -0.1700
Data Index: 1393502 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4905. Min Range: -7.4905
Max Act: 6.8655. Min Act: -0.1700
Data Index: 2994978 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4905. Min Range: -7.4905
Max Act: 6.8343. Min Act: -0.1700
Data Index: 4107224 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4905. Min Range: -7.4905
Max Act: 6.8343. Min Act: -0.1700
Data Index: 8663676 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4905. Min Range: -7.4905
Max Act: 6.8343. Min Act: -0.1700
Data Index: 1153563 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4905. Min Range: -7.4905
Max Act: 6.8343. Min Act: -0.1700
Data Index: 4531872 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4905. Min Range: -7.4905
Max Act: 6.8655. Min Act: -0.1700
Data Index: 5459115 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4905. Min Range: -7.4905
Max Act: 6.8343. Min Act: -0.1700
Data Index: 1025760 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4905. Min Range: -7.4905
Max Act: 6.8030. Min Act: -0.1700
Data Index: 504643 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4905. Min Range: -7.4905
Max Act: 6.8030. Min Act: -0.1700
Data Index: 4066618 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4905. Min Range: -7.4905
Max Act: 6.7718. Min Act: -0.1700
Data Index: 2503930 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4905. Min Range: -7.4905
Max Act: 6.7718. Min Act: -0.1700
Data Index: 492941 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19