Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1998 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7144. Min Range: -2.7144
Max Act: 2.7144. Min Act: -0.1700
Data Index: 377888 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7144. Min Range: -2.7144
Max Act: 2.6823. Min Act: -0.1700
Data Index: 676944 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7144. Min Range: -2.7144
Max Act: 2.6342. Min Act: -0.1700
Data Index: 1252361 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7144. Min Range: -2.7144
Max Act: 2.6503. Min Act: -0.1700
Data Index: 651134 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7144. Min Range: -2.7144
Max Act: 2.6182. Min Act: -0.1700
Data Index: 1300264 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7144. Min Range: -2.7144
Max Act: 2.6182. Min Act: -0.1700
Data Index: 493680 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7144. Min Range: -2.7144
Max Act: 2.6021. Min Act: -0.1700
Data Index: 1237333 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7144. Min Range: -2.7144
Max Act: 2.6342. Min Act: -0.1700
Data Index: 1222553 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7144. Min Range: -2.7144
Max Act: 2.6021. Min Act: -0.1700
Data Index: 102247 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7144. Min Range: -2.7144
Max Act: 2.6021. Min Act: -0.1700
Data Index: 993045 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7144. Min Range: -2.7144
Max Act: 2.5860. Min Act: -0.1700
Data Index: 1114099 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7144. Min Range: -2.7144
Max Act: 2.6021. Min Act: -0.1700
Data Index: 677446 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7144. Min Range: -2.7144
Max Act: 2.6021. Min Act: -0.1700
Data Index: 1210163 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7144. Min Range: -2.7144
Max Act: 2.6182. Min Act: -0.1700
Data Index: 134180 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7144. Min Range: -2.7144
Max Act: 2.5860. Min Act: -0.1700
Data Index: 774300 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7144. Min Range: -2.7144
Max Act: 2.6182. Min Act: -0.1700
Data Index: 741922 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7144. Min Range: -2.7144
Max Act: 2.5860. Min Act: -0.1700
Data Index: 304135 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7144. Min Range: -2.7144
Max Act: 2.5860. Min Act: -0.1700
Data Index: 882605 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7144. Min Range: -2.7144
Max Act: 2.5860. Min Act: -0.1700
Data Index: 150959 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7144. Min Range: -2.7144
Max Act: 2.5699. Min Act: -0.1700
Data Index: 651336 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19