Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1986 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7580. Min Range: -2.7580
Max Act: 2.7580. Min Act: -0.1700
Data Index: 126826 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7580. Min Range: -2.7580
Max Act: 2.7580. Min Act: -0.1700
Data Index: 265183 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7580. Min Range: -2.7580
Max Act: 2.7261. Min Act: -0.1700
Data Index: 159296 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7580. Min Range: -2.7580
Max Act: 2.7261. Min Act: -0.1700
Data Index: 753712 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7580. Min Range: -2.7580
Max Act: 2.7421. Min Act: -0.1700
Data Index: 183754 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7580. Min Range: -2.7580
Max Act: 2.7101. Min Act: -0.1700
Data Index: 555361 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7580. Min Range: -2.7580
Max Act: 2.7261. Min Act: -0.1700
Data Index: 715881 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7580. Min Range: -2.7580
Max Act: 2.7101. Min Act: -0.1700
Data Index: 700605 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7580. Min Range: -2.7580
Max Act: 2.7101. Min Act: -0.1700
Data Index: 1077944 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7580. Min Range: -2.7580
Max Act: 2.7101. Min Act: -0.1700
Data Index: 1228363 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7580. Min Range: -2.7580
Max Act: 2.6941. Min Act: -0.1700
Data Index: 971800 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7580. Min Range: -2.7580
Max Act: 2.6941. Min Act: -0.1700
Data Index: 905799 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7580. Min Range: -2.7580
Max Act: 2.6781. Min Act: -0.1700
Data Index: 1170983 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7580. Min Range: -2.7580
Max Act: 2.6941. Min Act: -0.1700
Data Index: 1023306 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7580. Min Range: -2.7580
Max Act: 2.6781. Min Act: -0.1700
Data Index: 659547 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7580. Min Range: -2.7580
Max Act: 2.6941. Min Act: -0.1700
Data Index: 160574 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7580. Min Range: -2.7580
Max Act: 2.6621. Min Act: -0.1700
Data Index: 1049158 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7580. Min Range: -2.7580
Max Act: 2.6781. Min Act: -0.1700
Data Index: 493808 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7580. Min Range: -2.7580
Max Act: 2.6781. Min Act: -0.1700
Data Index: 337735 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7580. Min Range: -2.7580
Max Act: 2.6781. Min Act: -0.1700
Data Index: 530300 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19