Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1965 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.8722. Min Range: -4.8722
Max Act: 4.8722. Min Act: -0.1700
Data Index: 96453 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8722. Min Range: -4.8722
Max Act: 4.7784. Min Act: -0.1700
Data Index: 586798 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8722. Min Range: -4.8722
Max Act: 4.7472. Min Act: -0.1700
Data Index: 250555 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8722. Min Range: -4.8722
Max Act: 4.7159. Min Act: -0.1700
Data Index: 381339 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8722. Min Range: -4.8722
Max Act: 4.7784. Min Act: -0.1700
Data Index: 987450 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8722. Min Range: -4.8722
Max Act: 4.7159. Min Act: -0.1700
Data Index: 753609 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8722. Min Range: -4.8722
Max Act: 4.7159. Min Act: -0.1700
Data Index: 708922 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8722. Min Range: -4.8722
Max Act: 4.6847. Min Act: -0.1698
Data Index: 623415 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8722. Min Range: -4.8722
Max Act: 4.6222. Min Act: -0.1700
Data Index: 607687 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8722. Min Range: -4.8722
Max Act: 4.6222. Min Act: -0.1700
Data Index: 1034652 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8722. Min Range: -4.8722
Max Act: 4.6222. Min Act: -0.1700
Data Index: 403036 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8722. Min Range: -4.8722
Max Act: 4.5597. Min Act: -0.1700
Data Index: 329962 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8722. Min Range: -4.8722
Max Act: 4.5909. Min Act: -0.1700
Data Index: 1100101 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8722. Min Range: -4.8722
Max Act: 4.5284. Min Act: -0.1699
Data Index: 505175 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8722. Min Range: -4.8722
Max Act: 4.5284. Min Act: -0.1700
Data Index: 462181 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8722. Min Range: -4.8722
Max Act: 4.5284. Min Act: -0.1700
Data Index: 895621 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8722. Min Range: -4.8722
Max Act: 4.5284. Min Act: -0.1700
Data Index: 819048 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8722. Min Range: -4.8722
Max Act: 4.5284. Min Act: -0.1699
Data Index: 37370 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8722. Min Range: -4.8722
Max Act: 4.5284. Min Act: -0.1700
Data Index: 119250 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8722. Min Range: -4.8722
Max Act: 4.5597. Min Act: -0.1700
Data Index: 757037 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19