Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1987 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.8930. Min Range: -4.8930
Max Act: 4.8930. Min Act: -0.1700
Data Index: 107492 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8930. Min Range: -4.8930
Max Act: 4.5805. Min Act: -0.1700
Data Index: 89285 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8930. Min Range: -4.8930
Max Act: 4.6117. Min Act: -0.1700
Data Index: 1268046 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8930. Min Range: -4.8930
Max Act: 4.6117. Min Act: -0.1699
Data Index: 1310279 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8930. Min Range: -4.8930
Max Act: 4.5805. Min Act: -0.1700
Data Index: 1235908 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8930. Min Range: -4.8930
Max Act: 4.6430. Min Act: -0.1700
Data Index: 1316853 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8930. Min Range: -4.8930
Max Act: 4.4867. Min Act: -0.1700
Data Index: 1036037 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8930. Min Range: -4.8930
Max Act: 4.5180. Min Act: -0.1700
Data Index: 970919 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8930. Min Range: -4.8930
Max Act: 4.4555. Min Act: -0.1700
Data Index: 1092430 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8930. Min Range: -4.8930
Max Act: 4.4555. Min Act: -0.1700
Data Index: 1200776 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8930. Min Range: -4.8930
Max Act: 4.4867. Min Act: -0.1700
Data Index: 1330272 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8930. Min Range: -4.8930
Max Act: 4.4867. Min Act: -0.1700
Data Index: 276539 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8930. Min Range: -4.8930
Max Act: 4.4867. Min Act: -0.1700
Data Index: 97711 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8930. Min Range: -4.8930
Max Act: 4.4555. Min Act: -0.1700
Data Index: 216003 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8930. Min Range: -4.8930
Max Act: 4.4555. Min Act: -0.1700
Data Index: 1279781 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8930. Min Range: -4.8930
Max Act: 4.3930. Min Act: -0.1700
Data Index: 233565 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8930. Min Range: -4.8930
Max Act: 4.3930. Min Act: -0.1700
Data Index: 968364 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8930. Min Range: -4.8930
Max Act: 4.3617. Min Act: -0.1700
Data Index: 791521 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8930. Min Range: -4.8930
Max Act: 4.4242. Min Act: -0.1700
Data Index: 1172798 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8930. Min Range: -4.8930
Max Act: 4.3930. Min Act: -0.1700
Data Index: 225827 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19