Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 28 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.7536. Min Act: -0.1700
Data Index: 634488 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.7377. Min Act: -0.1700
Data Index: 241342 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.7377. Min Act: -0.1700
Data Index: 497324 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.7217. Min Act: -0.1700
Data Index: 780438 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.7057. Min Act: -0.1700
Data Index: 399567 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.6897. Min Act: -0.1700
Data Index: 1254195 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.7057. Min Act: -0.1700
Data Index: 902760 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.6897. Min Act: -0.1700
Data Index: 873361 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.6737. Min Act: -0.1700
Data Index: 110747 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.6737. Min Act: -0.1700
Data Index: 970687 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.6897. Min Act: -0.1700
Data Index: 798129 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.7057. Min Act: -0.1700
Data Index: 376661 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.6737. Min Act: -0.1700
Data Index: 815941 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.6737. Min Act: -0.1700
Data Index: 511286 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.6737. Min Act: -0.1700
Data Index: 830807 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.6576. Min Act: -0.1700
Data Index: 793878 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.6576. Min Act: -0.1700
Data Index: 55508 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.6255. Min Act: -0.1700
Data Index: 847659 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.6576. Min Act: -0.1700
Data Index: 516044 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.6416. Min Act: -0.1700
Data Index: 531970 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19