Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 36 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9994. Min Range: -4.9994
Max Act: 4.9994. Min Act: -0.1700
Data Index: 374878 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9994. Min Range: -4.9994
Max Act: 4.8119. Min Act: -0.1700
Data Index: 1315622 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9994. Min Range: -4.9994
Max Act: 4.6244. Min Act: -0.1700
Data Index: 303041 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9994. Min Range: -4.9994
Max Act: 4.7181. Min Act: -0.1700
Data Index: 735586 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9994. Min Range: -4.9994
Max Act: 4.6556. Min Act: -0.1700
Data Index: 1004447 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9994. Min Range: -4.9994
Max Act: 4.5619. Min Act: -0.1700
Data Index: 311708 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9994. Min Range: -4.9994
Max Act: 4.5619. Min Act: -0.1700
Data Index: 616961 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9994. Min Range: -4.9994
Max Act: 4.5619. Min Act: -0.1700
Data Index: 1015111 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9994. Min Range: -4.9994
Max Act: 4.5306. Min Act: -0.1700
Data Index: 75771 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9994. Min Range: -4.9994
Max Act: 4.5619. Min Act: -0.1700
Data Index: 551636 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9994. Min Range: -4.9994
Max Act: 4.5931. Min Act: -0.1700
Data Index: 225716 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9994. Min Range: -4.9994
Max Act: 4.5931. Min Act: -0.1700
Data Index: 443912 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9994. Min Range: -4.9994
Max Act: 4.5619. Min Act: -0.1700
Data Index: 1215103 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9994. Min Range: -4.9994
Max Act: 4.5619. Min Act: -0.1700
Data Index: 708957 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9994. Min Range: -4.9994
Max Act: 4.5306. Min Act: -0.1700
Data Index: 1045939 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9994. Min Range: -4.9994
Max Act: 4.4056. Min Act: -0.1700
Data Index: 757291 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9994. Min Range: -4.9994
Max Act: 4.5619. Min Act: -0.1700
Data Index: 1028925 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9994. Min Range: -4.9994
Max Act: 4.5306. Min Act: -0.1700
Data Index: 828589 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9994. Min Range: -4.9994
Max Act: 4.4681. Min Act: -0.1700
Data Index: 647177 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9994. Min Range: -4.9994
Max Act: 4.5619. Min Act: -0.1700
Data Index: 658442 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19