Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1238 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.7070. Min Act: -0.1700
Data Index: 387183 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.5195. Min Act: -0.1700
Data Index: 89400 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.4570. Min Act: -0.1700
Data Index: 33096 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.4882. Min Act: -0.1700
Data Index: 1053161 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.3945. Min Act: -0.1700
Data Index: 1183895 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.4570. Min Act: -0.1700
Data Index: 1238122 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.4570. Min Act: -0.1700
Data Index: 308631 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.4257. Min Act: -0.1700
Data Index: 403406 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.4257. Min Act: -0.1700
Data Index: 1165725 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.3945. Min Act: -0.1700
Data Index: 1060477 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.3945. Min Act: -0.1700
Data Index: 1177768 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.4257. Min Act: -0.1700
Data Index: 1316701 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.3632. Min Act: -0.1700
Data Index: 1086867 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.3945. Min Act: -0.1700
Data Index: 1256651 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.3632. Min Act: -0.1700
Data Index: 33881 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.3945. Min Act: -0.1700
Data Index: 42495 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.3632. Min Act: -0.1700
Data Index: 332495 (C4 (Web Text))
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.3632. Min Act: -0.1700
Data Index: 548318 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.3632. Min Act: -0.1700
Data Index: 1196128 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.3320. Min Act: -0.1700
Data Index: 467484 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19