Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2040 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 6.9693. Min Range: -6.9693
Max Act: 6.9693. Min Act: -0.1700
Data Index: 724892 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9693. Min Range: -6.9693
Max Act: 6.7193. Min Act: -0.1700
Data Index: 300445 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9693. Min Range: -6.9693
Max Act: 6.6880. Min Act: -0.1700
Data Index: 519690 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9693. Min Range: -6.9693
Max Act: 6.7505. Min Act: -0.1700
Data Index: 1286341 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9693. Min Range: -6.9693
Max Act: 6.6568. Min Act: -0.1700
Data Index: 550086 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9693. Min Range: -6.9693
Max Act: 6.5630. Min Act: -0.1700
Data Index: 864533 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9693. Min Range: -6.9693
Max Act: 6.5943. Min Act: -0.1700
Data Index: 411911 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9693. Min Range: -6.9693
Max Act: 6.5943. Min Act: -0.1700
Data Index: 435642 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9693. Min Range: -6.9693
Max Act: 6.5943. Min Act: -0.1700
Data Index: 805161 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9693. Min Range: -6.9693
Max Act: 6.6255. Min Act: -0.1700
Data Index: 646849 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9693. Min Range: -6.9693
Max Act: 6.5943. Min Act: -0.1700
Data Index: 1201146 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9693. Min Range: -6.9693
Max Act: 6.5005. Min Act: -0.1700
Data Index: 32955 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9693. Min Range: -6.9693
Max Act: 6.5630. Min Act: -0.1700
Data Index: 260892 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9693. Min Range: -6.9693
Max Act: 6.5005. Min Act: -0.1700
Data Index: 955480 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9693. Min Range: -6.9693
Max Act: 6.4693. Min Act: -0.1700
Data Index: 18660 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9693. Min Range: -6.9693
Max Act: 6.5318. Min Act: -0.1700
Data Index: 508622 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9693. Min Range: -6.9693
Max Act: 6.4693. Min Act: -0.1700
Data Index: 305411 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9693. Min Range: -6.9693
Max Act: 6.4693. Min Act: -0.1700
Data Index: 325263 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9693. Min Range: -6.9693
Max Act: 6.4380. Min Act: -0.1700
Data Index: 385298 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9693. Min Range: -6.9693
Max Act: 6.4380. Min Act: -0.1700
Data Index: 18510 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19