Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 135 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5361. Min Range: -2.5361
Max Act: 2.5361. Min Act: -0.1700
Data Index: 983019 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5361. Min Range: -2.5361
Max Act: 2.5361. Min Act: -0.1700
Data Index: 42965 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5361. Min Range: -2.5361
Max Act: 2.5199. Min Act: -0.1700
Data Index: 1271118 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5361. Min Range: -2.5361
Max Act: 2.5199. Min Act: -0.1700
Data Index: 974672 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5361. Min Range: -2.5361
Max Act: 2.5037. Min Act: -0.1700
Data Index: 708672 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5361. Min Range: -2.5361
Max Act: 2.4875. Min Act: -0.1700
Data Index: 1292602 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5361. Min Range: -2.5361
Max Act: 2.4713. Min Act: -0.1700
Data Index: 60428 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5361. Min Range: -2.5361
Max Act: 2.4550. Min Act: -0.1700
Data Index: 674469 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5361. Min Range: -2.5361
Max Act: 2.4713. Min Act: -0.1700
Data Index: 1049142 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5361. Min Range: -2.5361
Max Act: 2.4388. Min Act: -0.1700
Data Index: 1566545 (Python Code)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5361. Min Range: -2.5361
Max Act: 2.4713. Min Act: -0.1700
Data Index: 609596 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5361. Min Range: -2.5361
Max Act: 2.4550. Min Act: -0.1700
Data Index: 130368 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5361. Min Range: -2.5361
Max Act: 2.4388. Min Act: -0.1700
Data Index: 1024068 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5361. Min Range: -2.5361
Max Act: 2.4225. Min Act: -0.1700
Data Index: 182794 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5361. Min Range: -2.5361
Max Act: 2.4225. Min Act: -0.1700
Data Index: 432348 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5361. Min Range: -2.5361
Max Act: 2.4388. Min Act: -0.1700
Data Index: 1173414 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5361. Min Range: -2.5361
Max Act: 2.4225. Min Act: -0.1700
Data Index: 1447593 (Python Code)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5361. Min Range: -2.5361
Max Act: 2.3899. Min Act: -0.1700
Data Index: 1227828 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5361. Min Range: -2.5361
Max Act: 2.4225. Min Act: -0.1700
Data Index: 25678 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5361. Min Range: -2.5361
Max Act: 2.4225. Min Act: -0.1700
Data Index: 1175779 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19