Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2017 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.5903. Min Range: -2.5903
Max Act: 2.5903. Min Act: -0.1700
Data Index: 1351836 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5903. Min Range: -2.5903
Max Act: 2.5096. Min Act: -0.1700
Data Index: 766064 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5903. Min Range: -2.5903
Max Act: 2.5096. Min Act: -0.1700
Data Index: 136476 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5903. Min Range: -2.5903
Max Act: 2.4772. Min Act: -0.1700
Data Index: 1142378 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5903. Min Range: -2.5903
Max Act: 2.4284. Min Act: -0.1700
Data Index: 1302499 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5903. Min Range: -2.5903
Max Act: 2.4610. Min Act: -0.1700
Data Index: 402895 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5903. Min Range: -2.5903
Max Act: 2.4610. Min Act: -0.1700
Data Index: 554951 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5903. Min Range: -2.5903
Max Act: 2.4284. Min Act: -0.1700
Data Index: 730353 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5903. Min Range: -2.5903
Max Act: 2.4284. Min Act: -0.1700
Data Index: 231200 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5903. Min Range: -2.5903
Max Act: 2.4447. Min Act: -0.1700
Data Index: 621799 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5903. Min Range: -2.5903
Max Act: 2.3958. Min Act: -0.1700
Data Index: 1143451 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5903. Min Range: -2.5903
Max Act: 2.3958. Min Act: -0.1700
Data Index: 646726 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5903. Min Range: -2.5903
Max Act: 2.3958. Min Act: -0.1700
Data Index: 430714 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5903. Min Range: -2.5903
Max Act: 2.4122. Min Act: -0.1700
Data Index: 70904 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5903. Min Range: -2.5903
Max Act: 2.3958. Min Act: -0.1700
Data Index: 400094 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5903. Min Range: -2.5903
Max Act: 2.4122. Min Act: -0.1700
Data Index: 522857 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5903. Min Range: -2.5903
Max Act: 2.3958. Min Act: -0.1700
Data Index: 262972 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5903. Min Range: -2.5903
Max Act: 2.3958. Min Act: -0.1700
Data Index: 351879 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5903. Min Range: -2.5903
Max Act: 2.3795. Min Act: -0.1700
Data Index: 291257 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5903. Min Range: -2.5903
Max Act: 2.3958. Min Act: -0.1700
Data Index: 1179865 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19