Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4072 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.7013. Min Range: -8.7013
Max Act: 8.6388. Min Act: -0.1700
Data Index: 1247708 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7013. Min Range: -8.7013
Max Act: 8.7013. Min Act: -0.1700
Data Index: 4899852 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7013. Min Range: -8.7013
Max Act: 8.6388. Min Act: -0.1700
Data Index: 3422046 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7013. Min Range: -8.7013
Max Act: 8.5138. Min Act: -0.1700
Data Index: 3544886 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7013. Min Range: -8.7013
Max Act: 8.5763. Min Act: -0.1700
Data Index: 4040077 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7013. Min Range: -8.7013
Max Act: 8.5138. Min Act: -0.1700
Data Index: 1238606 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7013. Min Range: -8.7013
Max Act: 8.5138. Min Act: -0.1700
Data Index: 3985773 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7013. Min Range: -8.7013
Max Act: 8.5138. Min Act: -0.1700
Data Index: 378447 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7013. Min Range: -8.7013
Max Act: 8.4513. Min Act: -0.1700
Data Index: 2949862 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7013. Min Range: -8.7013
Max Act: 8.4513. Min Act: -0.1700
Data Index: 5324573 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7013. Min Range: -8.7013
Max Act: 8.4513. Min Act: -0.1700
Data Index: 259238 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7013. Min Range: -8.7013
Max Act: 8.4513. Min Act: -0.1698
Data Index: 7871243 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7013. Min Range: -8.7013
Max Act: 8.4513. Min Act: -0.1700
Data Index: 3206449 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7013. Min Range: -8.7013
Max Act: 8.4513. Min Act: -0.1700
Data Index: 7342878 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7013. Min Range: -8.7013
Max Act: 8.4513. Min Act: -0.1700
Data Index: 6672233 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7013. Min Range: -8.7013
Max Act: 8.4513. Min Act: -0.1700
Data Index: 2754354 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7013. Min Range: -8.7013
Max Act: 8.4513. Min Act: -0.1700
Data Index: 2372955 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7013. Min Range: -8.7013
Max Act: 8.3263. Min Act: -0.1700
Data Index: 366398 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7013. Min Range: -8.7013
Max Act: 8.3888. Min Act: -0.1700
Data Index: 1089886 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7013. Min Range: -8.7013
Max Act: 8.3888. Min Act: -0.1700
Data Index: 3855501 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19