Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2036 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8927. Min Range: -2.8927
Max Act: 2.8927. Min Act: -0.1700
Data Index: 1304723 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8927. Min Range: -2.8927
Max Act: 2.8451. Min Act: -0.1700
Data Index: 863305 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8927. Min Range: -2.8927
Max Act: 2.8292. Min Act: -0.1700
Data Index: 302774 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8927. Min Range: -2.8927
Max Act: 2.8133. Min Act: -0.1700
Data Index: 33382 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8927. Min Range: -2.8927
Max Act: 2.8292. Min Act: -0.1700
Data Index: 294994 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8927. Min Range: -2.8927
Max Act: 2.8133. Min Act: -0.1700
Data Index: 617768 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8927. Min Range: -2.8927
Max Act: 2.8133. Min Act: -0.1700
Data Index: 645336 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8927. Min Range: -2.8927
Max Act: 2.8133. Min Act: -0.1700
Data Index: 1127369 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8927. Min Range: -2.8927
Max Act: 2.7973. Min Act: -0.1700
Data Index: 817405 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8927. Min Range: -2.8927
Max Act: 2.7973. Min Act: -0.1700
Data Index: 1238720 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8927. Min Range: -2.8927
Max Act: 2.7973. Min Act: -0.1700
Data Index: 440080 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8927. Min Range: -2.8927
Max Act: 2.7814. Min Act: -0.1700
Data Index: 255705 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8927. Min Range: -2.8927
Max Act: 2.7814. Min Act: -0.1700
Data Index: 879071 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8927. Min Range: -2.8927
Max Act: 2.7814. Min Act: -0.1700
Data Index: 899934 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8927. Min Range: -2.8927
Max Act: 2.7973. Min Act: -0.1700
Data Index: 1086598 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8927. Min Range: -2.8927
Max Act: 2.7973. Min Act: -0.1700
Data Index: 429176 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8927. Min Range: -2.8927
Max Act: 2.7814. Min Act: -0.1700
Data Index: 583028 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8927. Min Range: -2.8927
Max Act: 2.7814. Min Act: -0.1700
Data Index: 397277 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8927. Min Range: -2.8927
Max Act: 2.7655. Min Act: -0.1700
Data Index: 143031 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8927. Min Range: -2.8927
Max Act: 2.7655. Min Act: -0.1700
Data Index: 41105 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19