Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 109 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.1909. Min Range: -5.1909
Max Act: 5.1909. Min Act: -0.1700
Data Index: 489613 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1909. Min Range: -5.1909
Max Act: 5.1597. Min Act: -0.1700
Data Index: 931533 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1909. Min Range: -5.1909
Max Act: 4.8784. Min Act: -0.1700
Data Index: 264946 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1909. Min Range: -5.1909
Max Act: 4.9409. Min Act: -0.1700
Data Index: 463962 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1909. Min Range: -5.1909
Max Act: 4.9097. Min Act: -0.1700
Data Index: 715388 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1909. Min Range: -5.1909
Max Act: 4.8472. Min Act: -0.1700
Data Index: 362761 (C4 (Web Text))
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1909. Min Range: -5.1909
Max Act: 4.8159. Min Act: -0.1700
Data Index: 1106630 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1909. Min Range: -5.1909
Max Act: 4.9097. Min Act: -0.1700
Data Index: 483365 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1909. Min Range: -5.1909
Max Act: 4.8472. Min Act: -0.1700
Data Index: 938691 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1909. Min Range: -5.1909
Max Act: 4.8159. Min Act: -0.1700
Data Index: 964138 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1909. Min Range: -5.1909
Max Act: 4.8159. Min Act: -0.1700
Data Index: 885923 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1909. Min Range: -5.1909
Max Act: 4.6909. Min Act: -0.1700
Data Index: 212813 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1909. Min Range: -5.1909
Max Act: 4.8159. Min Act: -0.1700
Data Index: 43952 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1909. Min Range: -5.1909
Max Act: 4.7847. Min Act: -0.1700
Data Index: 512973 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1909. Min Range: -5.1909
Max Act: 4.8472. Min Act: -0.1699
Data Index: 1002570 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1909. Min Range: -5.1909
Max Act: 4.7222. Min Act: -0.1700
Data Index: 402952 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1909. Min Range: -5.1909
Max Act: 4.6284. Min Act: -0.1700
Data Index: 1163225 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1909. Min Range: -5.1909
Max Act: 4.7847. Min Act: -0.1700
Data Index: 251940 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1909. Min Range: -5.1909
Max Act: 4.6909. Min Act: -0.1700
Data Index: 1147296 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1909. Min Range: -5.1909
Max Act: 4.6284. Min Act: -0.1700
Data Index: 1058369 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19