Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3314 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2567. Min Range: -2.2567
Max Act: 2.2567. Min Act: -0.1700
Data Index: 5298752 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2567. Min Range: -2.2567
Max Act: 2.2236. Min Act: -0.1700
Data Index: 7599676 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2567. Min Range: -2.2567
Max Act: 2.1905. Min Act: -0.1700
Data Index: 7998374 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2567. Min Range: -2.2567
Max Act: 2.1572. Min Act: -0.1700
Data Index: 4054460 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2567. Min Range: -2.2567
Max Act: 2.1738. Min Act: -0.1700
Data Index: 392962 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2567. Min Range: -2.2567
Max Act: 2.1405. Min Act: -0.1700
Data Index: 3799023 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2567. Min Range: -2.2567
Max Act: 2.1405. Min Act: -0.1700
Data Index: 2696472 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2567. Min Range: -2.2567
Max Act: 2.1405. Min Act: -0.1700
Data Index: 62870 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2567. Min Range: -2.2567
Max Act: 2.1238. Min Act: -0.1700
Data Index: 3697527 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2567. Min Range: -2.2567
Max Act: 2.1071. Min Act: -0.1700
Data Index: 1941834 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2567. Min Range: -2.2567
Max Act: 2.0904. Min Act: -0.1700
Data Index: 5886060 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2567. Min Range: -2.2567
Max Act: 2.0904. Min Act: -0.1700
Data Index: 3981258 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2567. Min Range: -2.2567
Max Act: 2.0904. Min Act: -0.1700
Data Index: 2286487 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2567. Min Range: -2.2567
Max Act: 2.0904. Min Act: -0.1700
Data Index: 1139809 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2567. Min Range: -2.2567
Max Act: 2.1071. Min Act: -0.1700
Data Index: 7434626 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2567. Min Range: -2.2567
Max Act: 2.0736. Min Act: -0.1700
Data Index: 6971852 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2567. Min Range: -2.2567
Max Act: 2.0904. Min Act: -0.1700
Data Index: 4830570 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2567. Min Range: -2.2567
Max Act: 2.0568. Min Act: -0.1700
Data Index: 3779790 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2567. Min Range: -2.2567
Max Act: 2.0568. Min Act: -0.1700
Data Index: 1749960 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2567. Min Range: -2.2567
Max Act: 2.0568. Min Act: -0.1700
Data Index: 1050527 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19