Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1822 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9572. Min Range: -4.9572
Max Act: 4.9572. Min Act: -0.1700
Data Index: 974198 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9572. Min Range: -4.9572
Max Act: 4.8010. Min Act: -0.1700
Data Index: 318138 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9572. Min Range: -4.9572
Max Act: 4.7697. Min Act: -0.1700
Data Index: 300699 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9572. Min Range: -4.9572
Max Act: 4.7072. Min Act: -0.1700
Data Index: 406261 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9572. Min Range: -4.9572
Max Act: 4.6760. Min Act: -0.1700
Data Index: 92814 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9572. Min Range: -4.9572
Max Act: 4.7072. Min Act: -0.1700
Data Index: 953168 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9572. Min Range: -4.9572
Max Act: 4.7072. Min Act: -0.1700
Data Index: 101496 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9572. Min Range: -4.9572
Max Act: 4.7072. Min Act: -0.1700
Data Index: 617590 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9572. Min Range: -4.9572
Max Act: 4.6447. Min Act: -0.1700
Data Index: 956924 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9572. Min Range: -4.9572
Max Act: 4.6760. Min Act: -0.1700
Data Index: 300975 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9572. Min Range: -4.9572
Max Act: 4.6447. Min Act: -0.1700
Data Index: 156793 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9572. Min Range: -4.9572
Max Act: 4.6134. Min Act: -0.1700
Data Index: 838852 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9572. Min Range: -4.9572
Max Act: 4.5822. Min Act: -0.1700
Data Index: 1039465 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9572. Min Range: -4.9572
Max Act: 4.6134. Min Act: -0.1700
Data Index: 876276 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9572. Min Range: -4.9572
Max Act: 4.6134. Min Act: -0.1700
Data Index: 529544 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9572. Min Range: -4.9572
Max Act: 4.5509. Min Act: -0.1700
Data Index: 169173 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9572. Min Range: -4.9572
Max Act: 4.5822. Min Act: -0.1700
Data Index: 365105 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9572. Min Range: -4.9572
Max Act: 4.5822. Min Act: -0.1700
Data Index: 789237 (C4 (Web Text))
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9572. Min Range: -4.9572
Max Act: 4.5822. Min Act: -0.1700
Data Index: 58086 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9572. Min Range: -4.9572
Max Act: 4.5509. Min Act: -0.1700
Data Index: 443161 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19