Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1199 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0503. Min Range: -6.0503
Max Act: 6.0503. Min Act: -0.1700
Data Index: 1945632 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0503. Min Range: -6.0503
Max Act: 5.8628. Min Act: -0.1700
Data Index: 7160081 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0503. Min Range: -6.0503
Max Act: 5.8003. Min Act: -0.1700
Data Index: 4168536 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0503. Min Range: -6.0503
Max Act: 5.8003. Min Act: -0.1700
Data Index: 4779222 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0503. Min Range: -6.0503
Max Act: 5.8316. Min Act: -0.1700
Data Index: 4815056 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0503. Min Range: -6.0503
Max Act: 5.8316. Min Act: -0.1700
Data Index: 3251059 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0503. Min Range: -6.0503
Max Act: 5.8316. Min Act: -0.1700
Data Index: 5383793 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0503. Min Range: -6.0503
Max Act: 5.8003. Min Act: -0.1700
Data Index: 737961 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0503. Min Range: -6.0503
Max Act: 5.7378. Min Act: -0.1700
Data Index: 1651373 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0503. Min Range: -6.0503
Max Act: 5.7378. Min Act: -0.1700
Data Index: 7984385 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0503. Min Range: -6.0503
Max Act: 5.7378. Min Act: -0.1700
Data Index: 7811365 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0503. Min Range: -6.0503
Max Act: 5.7691. Min Act: -0.1700
Data Index: 4796572 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0503. Min Range: -6.0503
Max Act: 5.6753. Min Act: -0.1700
Data Index: 627363 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0503. Min Range: -6.0503
Max Act: 5.7066. Min Act: -0.1700
Data Index: 5189890 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0503. Min Range: -6.0503
Max Act: 5.6753. Min Act: -0.1700
Data Index: 6392895 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0503. Min Range: -6.0503
Max Act: 5.7066. Min Act: -0.1700
Data Index: 2294047 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0503. Min Range: -6.0503
Max Act: 5.6753. Min Act: -0.1700
Data Index: 2651801 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0503. Min Range: -6.0503
Max Act: 5.6753. Min Act: -0.1700
Data Index: 3435265 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0503. Min Range: -6.0503
Max Act: 5.6441. Min Act: -0.1700
Data Index: 2184997 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0503. Min Range: -6.0503
Max Act: 5.6441. Min Act: -0.1700
Data Index: 916502 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19