Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 914 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.8032. Min Range: -6.8032
Max Act: 6.8032. Min Act: -0.1700
Data Index: 7349 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8032. Min Range: -6.8032
Max Act: 6.7094. Min Act: -0.1700
Data Index: 193101 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8032. Min Range: -6.8032
Max Act: 6.6469. Min Act: -0.1700
Data Index: 681843 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8032. Min Range: -6.8032
Max Act: 6.6469. Min Act: -0.1700
Data Index: 576514 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8032. Min Range: -6.8032
Max Act: 6.6469. Min Act: -0.1700
Data Index: 1133720 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8032. Min Range: -6.8032
Max Act: 6.6469. Min Act: -0.1700
Data Index: 311259 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8032. Min Range: -6.8032
Max Act: 6.6469. Min Act: -0.1700
Data Index: 887139 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8032. Min Range: -6.8032
Max Act: 6.6157. Min Act: -0.1700
Data Index: 828028 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8032. Min Range: -6.8032
Max Act: 6.5532. Min Act: -0.1700
Data Index: 226001 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8032. Min Range: -6.8032
Max Act: 6.6469. Min Act: -0.1700
Data Index: 807924 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8032. Min Range: -6.8032
Max Act: 6.5219. Min Act: -0.1700
Data Index: 713298 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8032. Min Range: -6.8032
Max Act: 6.5844. Min Act: -0.1700
Data Index: 374196 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8032. Min Range: -6.8032
Max Act: 6.5532. Min Act: -0.1700
Data Index: 294625 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8032. Min Range: -6.8032
Max Act: 6.4907. Min Act: -0.1700
Data Index: 1333619 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8032. Min Range: -6.8032
Max Act: 6.4907. Min Act: -0.1700
Data Index: 284172 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8032. Min Range: -6.8032
Max Act: 6.5219. Min Act: -0.1700
Data Index: 520576 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8032. Min Range: -6.8032
Max Act: 6.4907. Min Act: -0.1700
Data Index: 755988 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8032. Min Range: -6.8032
Max Act: 6.4594. Min Act: -0.1700
Data Index: 101110 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8032. Min Range: -6.8032
Max Act: 6.4907. Min Act: -0.1700
Data Index: 13954 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8032. Min Range: -6.8032
Max Act: 6.4594. Min Act: -0.1700
Data Index: 294071 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19