Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 355 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.6649. Min Range: -2.6649
Max Act: 2.6649. Min Act: -0.1700
Data Index: 588172 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6649. Min Range: -2.6649
Max Act: 2.6489. Min Act: -0.1700
Data Index: 129861 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6649. Min Range: -2.6649
Max Act: 2.6329. Min Act: -0.1700
Data Index: 1165217 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6649. Min Range: -2.6649
Max Act: 2.6329. Min Act: -0.1700
Data Index: 91782 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6649. Min Range: -2.6649
Max Act: 2.6007. Min Act: -0.1700
Data Index: 509976 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6649. Min Range: -2.6649
Max Act: 2.5685. Min Act: -0.1700
Data Index: 876593 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6649. Min Range: -2.6649
Max Act: 2.5685. Min Act: -0.1700
Data Index: 628769 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6649. Min Range: -2.6649
Max Act: 2.5524. Min Act: -0.1700
Data Index: 1195740 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6649. Min Range: -2.6649
Max Act: 2.5524. Min Act: -0.1700
Data Index: 185253 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6649. Min Range: -2.6649
Max Act: 2.5685. Min Act: -0.1700
Data Index: 1334936 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6649. Min Range: -2.6649
Max Act: 2.5685. Min Act: -0.1700
Data Index: 1188275 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6649. Min Range: -2.6649
Max Act: 2.5524. Min Act: -0.1700
Data Index: 1233614 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6649. Min Range: -2.6649
Max Act: 2.5524. Min Act: -0.1700
Data Index: 27740 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6649. Min Range: -2.6649
Max Act: 2.5524. Min Act: -0.1700
Data Index: 1211021 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6649. Min Range: -2.6649
Max Act: 2.5524. Min Act: -0.1700
Data Index: 476592 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6649. Min Range: -2.6649
Max Act: 2.5524. Min Act: -0.1700
Data Index: 251816 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6649. Min Range: -2.6649
Max Act: 2.5524. Min Act: -0.1700
Data Index: 822550 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6649. Min Range: -2.6649
Max Act: 2.5524. Min Act: -0.1700
Data Index: 814264 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6649. Min Range: -2.6649
Max Act: 2.5524. Min Act: -0.1700
Data Index: 1309683 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6649. Min Range: -2.6649
Max Act: 2.5362. Min Act: -0.1700
Data Index: 277634 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19