Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1975 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.8877. Min Act: -0.1700
Data Index: 213857 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.8564. Min Act: -0.1700
Data Index: 259885 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.7939. Min Act: -0.1700
Data Index: 417434 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.8252. Min Act: -0.1700
Data Index: 1249808 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.7627. Min Act: -0.1700
Data Index: 878063 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.7314. Min Act: -0.1700
Data Index: 931345 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.7314. Min Act: -0.1700
Data Index: 231883 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.7001. Min Act: -0.1700
Data Index: 201290 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.7001. Min Act: -0.1700
Data Index: 968741 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.7314. Min Act: -0.1700
Data Index: 193305 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.7001. Min Act: -0.1700
Data Index: 55612 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.7001. Min Act: -0.1700
Data Index: 742125 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.7314. Min Act: -0.1700
Data Index: 290569 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.6689. Min Act: -0.1700
Data Index: 628494 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.7001. Min Act: -0.1700
Data Index: 777888 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.7001. Min Act: -0.1700
Data Index: 937118 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.6376. Min Act: -0.1700
Data Index: 593310 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.6689. Min Act: -0.1700
Data Index: 649549 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.6376. Min Act: -0.1700
Data Index: 143482 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8877. Min Range: -4.8877
Max Act: 4.7001. Min Act: -0.1700
Data Index: 864766 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19