Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 16 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6024. Min Range: -3.6024
Max Act: 3.6024. Min Act: -0.1700
Data Index: 3908348 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6024. Min Range: -3.6024
Max Act: 3.5868. Min Act: -0.1700
Data Index: 2313882 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6024. Min Range: -3.6024
Max Act: 3.5242. Min Act: -0.1700
Data Index: 5219826 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6024. Min Range: -3.6024
Max Act: 3.5398. Min Act: -0.1700
Data Index: 3417150 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6024. Min Range: -3.6024
Max Act: 3.5085. Min Act: -0.1700
Data Index: 4472696 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6024. Min Range: -3.6024
Max Act: 3.4772. Min Act: -0.1700
Data Index: 6226089 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6024. Min Range: -3.6024
Max Act: 3.4615. Min Act: -0.1700
Data Index: 4505983 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6024. Min Range: -3.6024
Max Act: 3.4302. Min Act: -0.1700
Data Index: 5648099 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6024. Min Range: -3.6024
Max Act: 3.4302. Min Act: -0.1700
Data Index: 5019571 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6024. Min Range: -3.6024
Max Act: 3.4145. Min Act: -0.1700
Data Index: 3960993 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6024. Min Range: -3.6024
Max Act: 3.4145. Min Act: -0.1700
Data Index: 103189 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6024. Min Range: -3.6024
Max Act: 3.3988. Min Act: -0.1700
Data Index: 2284111 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6024. Min Range: -3.6024
Max Act: 3.3831. Min Act: -0.1700
Data Index: 6816631 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6024. Min Range: -3.6024
Max Act: 3.3831. Min Act: -0.1700
Data Index: 824594 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6024. Min Range: -3.6024
Max Act: 3.3361. Min Act: -0.1700
Data Index: 5693132 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6024. Min Range: -3.6024
Max Act: 3.3518. Min Act: -0.1700
Data Index: 7559935 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6024. Min Range: -3.6024
Max Act: 3.3518. Min Act: -0.1700
Data Index: 8510683 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6024. Min Range: -3.6024
Max Act: 3.3204. Min Act: -0.1700
Data Index: 8638647 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6024. Min Range: -3.6024
Max Act: 3.3204. Min Act: -0.1700
Data Index: 8454518 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6024. Min Range: -3.6024
Max Act: 3.3204. Min Act: -0.1700
Data Index: 7732355 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19