Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2003 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.6512. Min Range: -2.6512
Max Act: 2.6512. Min Act: -0.1700
Data Index: 352262 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6512. Min Range: -2.6512
Max Act: 2.5869. Min Act: -0.1700
Data Index: 308237 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6512. Min Range: -2.6512
Max Act: 2.5708. Min Act: -0.1700
Data Index: 156970 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6512. Min Range: -2.6512
Max Act: 2.5385. Min Act: -0.1700
Data Index: 40055 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6512. Min Range: -2.6512
Max Act: 2.5385. Min Act: -0.1700
Data Index: 788370 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6512. Min Range: -2.6512
Max Act: 2.5224. Min Act: -0.1700
Data Index: 1353025 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6512. Min Range: -2.6512
Max Act: 2.5224. Min Act: -0.1700
Data Index: 1283278 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6512. Min Range: -2.6512
Max Act: 2.5224. Min Act: -0.1700
Data Index: 174864 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6512. Min Range: -2.6512
Max Act: 2.5224. Min Act: -0.1700
Data Index: 589677 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6512. Min Range: -2.6512
Max Act: 2.5224. Min Act: -0.1700
Data Index: 516471 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6512. Min Range: -2.6512
Max Act: 2.5062. Min Act: -0.1700
Data Index: 122847 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6512. Min Range: -2.6512
Max Act: 2.5062. Min Act: -0.1700
Data Index: 1180862 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6512. Min Range: -2.6512
Max Act: 2.5062. Min Act: -0.1700
Data Index: 863247 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6512. Min Range: -2.6512
Max Act: 2.5062. Min Act: -0.1700
Data Index: 651841 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6512. Min Range: -2.6512
Max Act: 2.5062. Min Act: -0.1700
Data Index: 373287 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6512. Min Range: -2.6512
Max Act: 2.5062. Min Act: -0.1700
Data Index: 603952 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6512. Min Range: -2.6512
Max Act: 2.5062. Min Act: -0.1700
Data Index: 125713 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6512. Min Range: -2.6512
Max Act: 2.5062. Min Act: -0.1700
Data Index: 1185101 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6512. Min Range: -2.6512
Max Act: 2.5224. Min Act: -0.1700
Data Index: 206772 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6512. Min Range: -2.6512
Max Act: 2.5062. Min Act: -0.1700
Data Index: 783998 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19