Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1983 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.5513. Min Range: -5.5513
Max Act: 5.5513. Min Act: -0.1700
Data Index: 173264 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5513. Min Range: -5.5513
Max Act: 5.4888. Min Act: -0.1700
Data Index: 384197 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5513. Min Range: -5.5513
Max Act: 5.5513. Min Act: -0.1700
Data Index: 33905 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5513. Min Range: -5.5513
Max Act: 5.4576. Min Act: -0.1700
Data Index: 305218 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5513. Min Range: -5.5513
Max Act: 5.5513. Min Act: -0.1700
Data Index: 265299 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5513. Min Range: -5.5513
Max Act: 5.4576. Min Act: -0.1700
Data Index: 1118601 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5513. Min Range: -5.5513
Max Act: 5.4888. Min Act: -0.1700
Data Index: 1280657 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5513. Min Range: -5.5513
Max Act: 5.4888. Min Act: -0.1700
Data Index: 182869 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5513. Min Range: -5.5513
Max Act: 5.3951. Min Act: -0.1700
Data Index: 1332312 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5513. Min Range: -5.5513
Max Act: 5.3951. Min Act: -0.1700
Data Index: 661283 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5513. Min Range: -5.5513
Max Act: 5.3951. Min Act: -0.1700
Data Index: 338836 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5513. Min Range: -5.5513
Max Act: 5.3951. Min Act: -0.1700
Data Index: 1277851 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5513. Min Range: -5.5513
Max Act: 5.3951. Min Act: -0.1700
Data Index: 655791 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5513. Min Range: -5.5513
Max Act: 5.3951. Min Act: -0.1700
Data Index: 1104454 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5513. Min Range: -5.5513
Max Act: 5.3951. Min Act: -0.1700
Data Index: 527633 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5513. Min Range: -5.5513
Max Act: 5.3951. Min Act: -0.1700
Data Index: 451224 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5513. Min Range: -5.5513
Max Act: 5.3326. Min Act: -0.1700
Data Index: 396618 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5513. Min Range: -5.5513
Max Act: 5.3326. Min Act: -0.1700
Data Index: 726932 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5513. Min Range: -5.5513
Max Act: 5.3326. Min Act: -0.1700
Data Index: 480350 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5513. Min Range: -5.5513
Max Act: 5.3013. Min Act: -0.1700
Data Index: 107930 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19