Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4472 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7538. Min Range: -7.7538
Max Act: 7.7538. Min Act: -0.1700
Data Index: 8728520 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7538. Min Range: -7.7538
Max Act: 7.6601. Min Act: -0.1700
Data Index: 5298804 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7538. Min Range: -7.7538
Max Act: 7.6601. Min Act: -0.1700
Data Index: 1939313 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7538. Min Range: -7.7538
Max Act: 7.6601. Min Act: -0.1700
Data Index: 8820989 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7538. Min Range: -7.7538
Max Act: 7.6601. Min Act: -0.1700
Data Index: 570181 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7538. Min Range: -7.7538
Max Act: 7.5663. Min Act: -0.1700
Data Index: 6925973 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7538. Min Range: -7.7538
Max Act: 7.5038. Min Act: -0.1700
Data Index: 2232703 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7538. Min Range: -7.7538
Max Act: 7.4413. Min Act: -0.1700
Data Index: 7919784 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7538. Min Range: -7.7538
Max Act: 7.4101. Min Act: -0.1700
Data Index: 23646 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7538. Min Range: -7.7538
Max Act: 7.4101. Min Act: -0.1700
Data Index: 5547651 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7538. Min Range: -7.7538
Max Act: 7.3788. Min Act: -0.1700
Data Index: 799555 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7538. Min Range: -7.7538
Max Act: 7.3788. Min Act: -0.1700
Data Index: 1885145 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7538. Min Range: -7.7538
Max Act: 7.3788. Min Act: -0.1700
Data Index: 4186333 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7538. Min Range: -7.7538
Max Act: 7.3476. Min Act: -0.1700
Data Index: 8623825 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7538. Min Range: -7.7538
Max Act: 7.3476. Min Act: -0.1700
Data Index: 3710158 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7538. Min Range: -7.7538
Max Act: 7.3476. Min Act: -0.1700
Data Index: 2907898 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7538. Min Range: -7.7538
Max Act: 7.3476. Min Act: -0.1700
Data Index: 930879 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7538. Min Range: -7.7538
Max Act: 7.3476. Min Act: -0.1700
Data Index: 1129987 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7538. Min Range: -7.7538
Max Act: 7.3163. Min Act: -0.1700
Data Index: 6004761 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7538. Min Range: -7.7538
Max Act: 7.2851. Min Act: -0.1700
Data Index: 6566234 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19