Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3121 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3003. Min Range: -6.3003
Max Act: 6.3003. Min Act: -0.1700
Data Index: 7475660 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3003. Min Range: -6.3003
Max Act: 6.2066. Min Act: -0.1700
Data Index: 68779 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3003. Min Range: -6.3003
Max Act: 5.9878. Min Act: -0.1700
Data Index: 3111495 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3003. Min Range: -6.3003
Max Act: 5.9566. Min Act: -0.1700
Data Index: 8579164 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3003. Min Range: -6.3003
Max Act: 5.9566. Min Act: -0.1700
Data Index: 4553096 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3003. Min Range: -6.3003
Max Act: 5.9566. Min Act: -0.1700
Data Index: 8049784 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3003. Min Range: -6.3003
Max Act: 5.8941. Min Act: -0.1700
Data Index: 893857 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3003. Min Range: -6.3003
Max Act: 5.8316. Min Act: -0.1700
Data Index: 79777 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3003. Min Range: -6.3003
Max Act: 5.8316. Min Act: -0.1700
Data Index: 6239905 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3003. Min Range: -6.3003
Max Act: 5.8316. Min Act: -0.1700
Data Index: 574896 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3003. Min Range: -6.3003
Max Act: 5.7691. Min Act: -0.1700
Data Index: 7831714 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3003. Min Range: -6.3003
Max Act: 5.8003. Min Act: -0.1700
Data Index: 4384454 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3003. Min Range: -6.3003
Max Act: 5.8003. Min Act: -0.1700
Data Index: 943478 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3003. Min Range: -6.3003
Max Act: 5.8003. Min Act: -0.1700
Data Index: 3030995 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3003. Min Range: -6.3003
Max Act: 5.8003. Min Act: -0.1700
Data Index: 2145197 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3003. Min Range: -6.3003
Max Act: 5.7378. Min Act: -0.1700
Data Index: 3030999 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3003. Min Range: -6.3003
Max Act: 5.7378. Min Act: -0.1700
Data Index: 300745 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3003. Min Range: -6.3003
Max Act: 5.7066. Min Act: -0.1700
Data Index: 1920482 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3003. Min Range: -6.3003
Max Act: 5.7378. Min Act: -0.1700
Data Index: 1081952 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3003. Min Range: -6.3003
Max Act: 5.7378. Min Act: -0.1700
Data Index: 5951339 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19