Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4529 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6609. Min Range: -4.6609
Max Act: 4.6609. Min Act: -0.1700
Data Index: 2634391 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6609. Min Range: -4.6609
Max Act: 4.5359. Min Act: -0.1700
Data Index: 345149 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6609. Min Range: -4.6609
Max Act: 4.4734. Min Act: -0.1700
Data Index: 2551069 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6609. Min Range: -4.6609
Max Act: 4.4734. Min Act: -0.1700
Data Index: 8786861 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6609. Min Range: -4.6609
Max Act: 4.2859. Min Act: -0.1700
Data Index: 8069108 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6609. Min Range: -4.6609
Max Act: 4.2547. Min Act: -0.1700
Data Index: 7891125 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6609. Min Range: -4.6609
Max Act: 4.2234. Min Act: -0.1700
Data Index: 2164819 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6609. Min Range: -4.6609
Max Act: 4.2234. Min Act: -0.1700
Data Index: 5741682 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6609. Min Range: -4.6609
Max Act: 4.1922. Min Act: -0.1700
Data Index: 2164818 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6609. Min Range: -4.6609
Max Act: 4.1922. Min Act: -0.1700
Data Index: 1791098 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6609. Min Range: -4.6609
Max Act: 4.1609. Min Act: -0.1700
Data Index: 7310765 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6609. Min Range: -4.6609
Max Act: 4.0984. Min Act: -0.1700
Data Index: 4756592 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6609. Min Range: -4.6609
Max Act: 4.0359. Min Act: -0.1700
Data Index: 6446216 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6609. Min Range: -4.6609
Max Act: 4.0046. Min Act: -0.1700
Data Index: 5730210 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6609. Min Range: -4.6609
Max Act: 4.0046. Min Act: -0.1700
Data Index: 5142150 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6609. Min Range: -4.6609
Max Act: 4.0359. Min Act: -0.1700
Data Index: 3074218 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6609. Min Range: -4.6609
Max Act: 3.9734. Min Act: -0.1700
Data Index: 1604730 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6609. Min Range: -4.6609
Max Act: 3.9734. Min Act: -0.1700
Data Index: 2515464 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6609. Min Range: -4.6609
Max Act: 3.9734. Min Act: -0.1700
Data Index: 2164817 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6609. Min Range: -4.6609
Max Act: 3.9108. Min Act: -0.1700
Data Index: 5335707 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19