Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 16 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2999. Min Range: -7.2999
Max Act: 7.2999. Min Act: -0.1700
Data Index: 789516 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2999. Min Range: -7.2999
Max Act: 7.1749. Min Act: -0.1700
Data Index: 4600415 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2999. Min Range: -7.2999
Max Act: 7.1749. Min Act: -0.1700
Data Index: 2548439 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2999. Min Range: -7.2999
Max Act: 6.9874. Min Act: -0.1700
Data Index: 2656276 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2999. Min Range: -7.2999
Max Act: 6.9562. Min Act: -0.1700
Data Index: 3043788 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2999. Min Range: -7.2999
Max Act: 6.8937. Min Act: -0.1700
Data Index: 7947380 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2999. Min Range: -7.2999
Max Act: 6.8624. Min Act: -0.1700
Data Index: 3915208 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2999. Min Range: -7.2999
Max Act: 6.8624. Min Act: -0.1700
Data Index: 2960697 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2999. Min Range: -7.2999
Max Act: 6.7999. Min Act: -0.1700
Data Index: 8222264 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2999. Min Range: -7.2999
Max Act: 6.7687. Min Act: -0.1700
Data Index: 7350889 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2999. Min Range: -7.2999
Max Act: 6.7687. Min Act: -0.1700
Data Index: 3324469 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2999. Min Range: -7.2999
Max Act: 6.7374. Min Act: -0.1700
Data Index: 1326681 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2999. Min Range: -7.2999
Max Act: 6.7374. Min Act: -0.1700
Data Index: 956791 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2999. Min Range: -7.2999
Max Act: 6.7062. Min Act: -0.1700
Data Index: 2099554 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2999. Min Range: -7.2999
Max Act: 6.7062. Min Act: -0.1700
Data Index: 3158554 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2999. Min Range: -7.2999
Max Act: 6.7374. Min Act: -0.1700
Data Index: 1282708 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2999. Min Range: -7.2999
Max Act: 6.6749. Min Act: -0.1700
Data Index: 987342 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2999. Min Range: -7.2999
Max Act: 6.6437. Min Act: -0.1700
Data Index: 3526133 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2999. Min Range: -7.2999
Max Act: 6.7062. Min Act: -0.1700
Data Index: 6574417 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2999. Min Range: -7.2999
Max Act: 6.6749. Min Act: -0.1700
Data Index: 4234745 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19