Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 91 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.0510. Min Range: -3.0510
Max Act: 3.0510. Min Act: -0.1700
Data Index: 356382 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0510. Min Range: -3.0510
Max Act: 3.0510. Min Act: -0.1700
Data Index: 925977 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0510. Min Range: -3.0510
Max Act: 3.0194. Min Act: -0.1700
Data Index: 209454 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0510. Min Range: -3.0510
Max Act: 3.0036. Min Act: -0.1700
Data Index: 788478 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0510. Min Range: -3.0510
Max Act: 2.9878. Min Act: -0.1700
Data Index: 44372 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0510. Min Range: -3.0510
Max Act: 2.8927. Min Act: -0.1700
Data Index: 1152832 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0510. Min Range: -3.0510
Max Act: 2.8610. Min Act: -0.1700
Data Index: 283147 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0510. Min Range: -3.0510
Max Act: 2.8769. Min Act: -0.1700
Data Index: 1219170 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0510. Min Range: -3.0510
Max Act: 2.8769. Min Act: -0.1700
Data Index: 501337 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0510. Min Range: -3.0510
Max Act: 2.8610. Min Act: -0.1700
Data Index: 28501 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0510. Min Range: -3.0510
Max Act: 2.8451. Min Act: -0.1700
Data Index: 441130 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0510. Min Range: -3.0510
Max Act: 2.8610. Min Act: -0.1700
Data Index: 870440 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0510. Min Range: -3.0510
Max Act: 2.8451. Min Act: -0.1700
Data Index: 586835 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0510. Min Range: -3.0510
Max Act: 2.8451. Min Act: -0.1700
Data Index: 159512 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0510. Min Range: -3.0510
Max Act: 2.8451. Min Act: -0.1700
Data Index: 613129 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0510. Min Range: -3.0510
Max Act: 2.8451. Min Act: -0.1700
Data Index: 663610 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0510. Min Range: -3.0510
Max Act: 2.8451. Min Act: -0.1700
Data Index: 59271 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0510. Min Range: -3.0510
Max Act: 2.8292. Min Act: -0.1700
Data Index: 949389 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0510. Min Range: -3.0510
Max Act: 2.8292. Min Act: -0.1700
Data Index: 899376 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0510. Min Range: -3.0510
Max Act: 2.8292. Min Act: -0.1699
Data Index: 554438 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19