Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1349 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0607. Min Range: -8.0607
Max Act: 8.0607. Min Act: -0.1700
Data Index: 5036491 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0607. Min Range: -8.0607
Max Act: 7.9982. Min Act: -0.1700
Data Index: 6862851 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0607. Min Range: -8.0607
Max Act: 7.9357. Min Act: -0.1700
Data Index: 8443669 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0607. Min Range: -8.0607
Max Act: 7.5919. Min Act: -0.1700
Data Index: 4951057 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0607. Min Range: -8.0607
Max Act: 7.5294. Min Act: -0.1700
Data Index: 1233083 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0607. Min Range: -8.0607
Max Act: 7.4669. Min Act: -0.1700
Data Index: 4908430 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0607. Min Range: -8.0607
Max Act: 7.4669. Min Act: -0.1700
Data Index: 2120834 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0607. Min Range: -8.0607
Max Act: 7.4357. Min Act: -0.1700
Data Index: 2249997 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0607. Min Range: -8.0607
Max Act: 7.4357. Min Act: -0.1700
Data Index: 23328 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0607. Min Range: -8.0607
Max Act: 7.4044. Min Act: -0.1700
Data Index: 4160599 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0607. Min Range: -8.0607
Max Act: 7.3419. Min Act: -0.1700
Data Index: 6865916 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0607. Min Range: -8.0607
Max Act: 7.3419. Min Act: -0.1700
Data Index: 8539708 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0607. Min Range: -8.0607
Max Act: 7.3107. Min Act: -0.1700
Data Index: 7949814 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0607. Min Range: -8.0607
Max Act: 7.3107. Min Act: -0.1700
Data Index: 2647529 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0607. Min Range: -8.0607
Max Act: 7.2794. Min Act: -0.1700
Data Index: 5293482 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0607. Min Range: -8.0607
Max Act: 7.2482. Min Act: -0.1700
Data Index: 96889 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0607. Min Range: -8.0607
Max Act: 7.3107. Min Act: -0.1700
Data Index: 3910084 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0607. Min Range: -8.0607
Max Act: 7.3107. Min Act: -0.1700
Data Index: 2880222 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0607. Min Range: -8.0607
Max Act: 7.3107. Min Act: -0.1700
Data Index: 4090067 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0607. Min Range: -8.0607
Max Act: 7.2482. Min Act: -0.1700
Data Index: 7474840 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #19