Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 699 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8049. Min Range: -3.8049
Max Act: 3.7737. Min Act: -0.1700
Data Index: 3787393 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8049. Min Range: -3.8049
Max Act: 3.8049. Min Act: -0.1700
Data Index: 1250429 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8049. Min Range: -3.8049
Max Act: 3.7268. Min Act: -0.1700
Data Index: 3406878 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8049. Min Range: -3.8049
Max Act: 3.6798. Min Act: -0.1700
Data Index: 4905955 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8049. Min Range: -3.8049
Max Act: 3.6642. Min Act: -0.1700
Data Index: 1185199 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8049. Min Range: -3.8049
Max Act: 3.6172. Min Act: -0.1700
Data Index: 3406883 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8049. Min Range: -3.8049
Max Act: 3.6172. Min Act: -0.1700
Data Index: 1286552 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8049. Min Range: -3.8049
Max Act: 3.5859. Min Act: -0.1700
Data Index: 8215949 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8049. Min Range: -3.8049
Max Act: 3.5703. Min Act: -0.1700
Data Index: 4798426 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8049. Min Range: -3.8049
Max Act: 3.5859. Min Act: -0.1700
Data Index: 234029 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8049. Min Range: -3.8049
Max Act: 3.6016. Min Act: -0.1700
Data Index: 2576254 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8049. Min Range: -3.8049
Max Act: 3.5546. Min Act: -0.1700
Data Index: 8681017 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8049. Min Range: -3.8049
Max Act: 3.5703. Min Act: -0.1700
Data Index: 4886290 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8049. Min Range: -3.8049
Max Act: 3.5546. Min Act: -0.1700
Data Index: 3429543 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8049. Min Range: -3.8049
Max Act: 3.5703. Min Act: -0.1700
Data Index: 3406873 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8049. Min Range: -3.8049
Max Act: 3.5233. Min Act: -0.1700
Data Index: 4169893 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8049. Min Range: -3.8049
Max Act: 3.5390. Min Act: -0.1700
Data Index: 7283305 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8049. Min Range: -3.8049
Max Act: 3.5546. Min Act: -0.1700
Data Index: 7283308 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8049. Min Range: -3.8049
Max Act: 3.5390. Min Act: -0.1700
Data Index: 8434679 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8049. Min Range: -3.8049
Max Act: 3.5390. Min Act: -0.1700
Data Index: 2646118 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19