Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3692 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3441. Min Range: -8.3441
Max Act: 8.3441. Min Act: -0.1700
Data Index: 4636577 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3441. Min Range: -8.3441
Max Act: 7.9066. Min Act: -0.1700
Data Index: 3082358 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3441. Min Range: -8.3441
Max Act: 7.7191. Min Act: -0.1700
Data Index: 772333 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3441. Min Range: -8.3441
Max Act: 7.6566. Min Act: -0.1700
Data Index: 7764567 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3441. Min Range: -8.3441
Max Act: 7.5941. Min Act: -0.1700
Data Index: 7172207 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3441. Min Range: -8.3441
Max Act: 7.3753. Min Act: -0.1700
Data Index: 228162 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3441. Min Range: -8.3441
Max Act: 7.4066. Min Act: -0.1700
Data Index: 1615643 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3441. Min Range: -8.3441
Max Act: 7.4378. Min Act: -0.1700
Data Index: 4181721 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3441. Min Range: -8.3441
Max Act: 7.4691. Min Act: -0.1700
Data Index: 4841190 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3441. Min Range: -8.3441
Max Act: 7.3753. Min Act: -0.1700
Data Index: 3625555 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3441. Min Range: -8.3441
Max Act: 7.4066. Min Act: -0.1700
Data Index: 8532476 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3441. Min Range: -8.3441
Max Act: 7.3128. Min Act: -0.1700
Data Index: 5927745 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3441. Min Range: -8.3441
Max Act: 7.3753. Min Act: -0.1700
Data Index: 8391382 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3441. Min Range: -8.3441
Max Act: 7.3441. Min Act: -0.1700
Data Index: 409924 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3441. Min Range: -8.3441
Max Act: 7.3441. Min Act: -0.1700
Data Index: 8752808 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3441. Min Range: -8.3441
Max Act: 7.2816. Min Act: -0.1700
Data Index: 3058854 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3441. Min Range: -8.3441
Max Act: 7.2503. Min Act: -0.1700
Data Index: 2548379 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3441. Min Range: -8.3441
Max Act: 7.2503. Min Act: -0.1700
Data Index: 787093 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3441. Min Range: -8.3441
Max Act: 7.2816. Min Act: -0.1700
Data Index: 784949 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3441. Min Range: -8.3441
Max Act: 7.1878. Min Act: -0.1700
Data Index: 947635 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19