Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2015 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0807. Min Range: -3.0807
Max Act: 3.0807. Min Act: -0.1700
Data Index: 560566 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0807. Min Range: -3.0807
Max Act: 3.0334. Min Act: -0.1700
Data Index: 554142 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0807. Min Range: -3.0807
Max Act: 3.0176. Min Act: -0.1700
Data Index: 1269136 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0807. Min Range: -3.0807
Max Act: 2.9543. Min Act: -0.1700
Data Index: 812011 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0807. Min Range: -3.0807
Max Act: 2.9226. Min Act: -0.1700
Data Index: 894372 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0807. Min Range: -3.0807
Max Act: 2.9385. Min Act: -0.1700
Data Index: 230180 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0807. Min Range: -3.0807
Max Act: 2.9068. Min Act: -0.1700
Data Index: 656769 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0807. Min Range: -3.0807
Max Act: 2.8909. Min Act: -0.1700
Data Index: 176784 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0807. Min Range: -3.0807
Max Act: 2.8909. Min Act: -0.1700
Data Index: 1353036 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0807. Min Range: -3.0807
Max Act: 2.8750. Min Act: -0.1700
Data Index: 581303 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0807. Min Range: -3.0807
Max Act: 2.8750. Min Act: -0.1700
Data Index: 587709 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0807. Min Range: -3.0807
Max Act: 2.8750. Min Act: -0.1700
Data Index: 1004189 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0807. Min Range: -3.0807
Max Act: 2.8591. Min Act: -0.1700
Data Index: 700074 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0807. Min Range: -3.0807
Max Act: 2.8591. Min Act: -0.1700
Data Index: 1052983 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0807. Min Range: -3.0807
Max Act: 2.8591. Min Act: -0.1700
Data Index: 768099 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0807. Min Range: -3.0807
Max Act: 2.8591. Min Act: -0.1700
Data Index: 378699 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0807. Min Range: -3.0807
Max Act: 2.8591. Min Act: -0.1700
Data Index: 520768 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0807. Min Range: -3.0807
Max Act: 2.8433. Min Act: -0.1700
Data Index: 449178 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0807. Min Range: -3.0807
Max Act: 2.8274. Min Act: -0.1700
Data Index: 609766 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0807. Min Range: -3.0807
Max Act: 2.8433. Min Act: -0.1700
Data Index: 323518 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19