Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 8 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.7545. Min Range: -4.7545
Max Act: 4.7545. Min Act: -0.1700
Data Index: 126188 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7545. Min Range: -4.7545
Max Act: 4.7545. Min Act: -0.1700
Data Index: 647148 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7545. Min Range: -4.7545
Max Act: 4.7232. Min Act: -0.1700
Data Index: 830860 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7545. Min Range: -4.7545
Max Act: 4.6920. Min Act: -0.1700
Data Index: 1359687 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7545. Min Range: -4.7545
Max Act: 4.6920. Min Act: -0.1700
Data Index: 546375 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7545. Min Range: -4.7545
Max Act: 4.6920. Min Act: -0.1698
Data Index: 769042 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7545. Min Range: -4.7545
Max Act: 4.6607. Min Act: -0.1700
Data Index: 396929 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7545. Min Range: -4.7545
Max Act: 4.6607. Min Act: -0.1700
Data Index: 345159 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7545. Min Range: -4.7545
Max Act: 4.6607. Min Act: -0.1700
Data Index: 736473 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7545. Min Range: -4.7545
Max Act: 4.6607. Min Act: -0.1700
Data Index: 874815 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7545. Min Range: -4.7545
Max Act: 4.5982. Min Act: -0.1700
Data Index: 171431 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7545. Min Range: -4.7545
Max Act: 4.6295. Min Act: -0.1700
Data Index: 973384 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7545. Min Range: -4.7545
Max Act: 4.6295. Min Act: -0.1700
Data Index: 720189 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7545. Min Range: -4.7545
Max Act: 4.6295. Min Act: -0.1700
Data Index: 1116471 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7545. Min Range: -4.7545
Max Act: 4.5982. Min Act: -0.1700
Data Index: 632697 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7545. Min Range: -4.7545
Max Act: 4.6295. Min Act: -0.1700
Data Index: 82786 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7545. Min Range: -4.7545
Max Act: 4.5982. Min Act: -0.1657
Data Index: 532179 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7545. Min Range: -4.7545
Max Act: 4.5670. Min Act: -0.1700
Data Index: 493297 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7545. Min Range: -4.7545
Max Act: 4.6295. Min Act: -0.1700
Data Index: 1097259 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7545. Min Range: -4.7545
Max Act: 4.6295. Min Act: -0.1700
Data Index: 110775 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19