Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 26 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4902. Min Range: -2.4902
Max Act: 2.4902. Min Act: -0.1697
Data Index: 621816 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4902. Min Range: -2.4902
Max Act: 2.4415. Min Act: -0.1652
Data Index: 1063934 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4902. Min Range: -2.4902
Max Act: 2.3763. Min Act: -0.1652
Data Index: 1036914 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4902. Min Range: -2.4902
Max Act: 2.3763. Min Act: -0.1652
Data Index: 1134643 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4902. Min Range: -2.4902
Max Act: 2.3763. Min Act: -0.1652
Data Index: 964755 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4902. Min Range: -2.4902
Max Act: 2.3763. Min Act: -0.1655
Data Index: 575472 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4902. Min Range: -2.4902
Max Act: 2.3600. Min Act: -0.1666
Data Index: 30164 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4902. Min Range: -2.4902
Max Act: 2.3600. Min Act: -0.1652
Data Index: 280806 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4902. Min Range: -2.4902
Max Act: 2.3600. Min Act: -0.1695
Data Index: 497067 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4902. Min Range: -2.4902
Max Act: 2.3436. Min Act: -0.1652
Data Index: 529196 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4902. Min Range: -2.4902
Max Act: 2.3600. Min Act: -0.1652
Data Index: 593230 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4902. Min Range: -2.4902
Max Act: 2.3436. Min Act: -0.1652
Data Index: 1217279 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4902. Min Range: -2.4902
Max Act: 2.3436. Min Act: -0.1670
Data Index: 753996 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4902. Min Range: -2.4902
Max Act: 2.3272. Min Act: -0.1652
Data Index: 1277654 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4902. Min Range: -2.4902
Max Act: 2.3272. Min Act: -0.1668
Data Index: 689850 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4902. Min Range: -2.4902
Max Act: 2.3272. Min Act: -0.1700
Data Index: 1135148 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4902. Min Range: -2.4902
Max Act: 2.2943. Min Act: -0.1652
Data Index: 310683 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4902. Min Range: -2.4902
Max Act: 2.3108. Min Act: -0.1652
Data Index: 613584 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4902. Min Range: -2.4902
Max Act: 2.3108. Min Act: -0.1680
Data Index: 1106330 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4902. Min Range: -2.4902
Max Act: 2.3108. Min Act: -0.1652
Data Index: 172178 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19