Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2035 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6885. Min Range: -2.6885
Max Act: 2.6885. Min Act: -0.1700
Data Index: 669179 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6885. Min Range: -2.6885
Max Act: 2.6725. Min Act: -0.1700
Data Index: 445190 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6885. Min Range: -2.6885
Max Act: 2.6725. Min Act: -0.1700
Data Index: 967941 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6885. Min Range: -2.6885
Max Act: 2.6725. Min Act: -0.1700
Data Index: 447332 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6885. Min Range: -2.6885
Max Act: 2.6564. Min Act: -0.1700
Data Index: 454159 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6885. Min Range: -2.6885
Max Act: 2.6564. Min Act: -0.1700
Data Index: 548931 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6885. Min Range: -2.6885
Max Act: 2.6564. Min Act: -0.1700
Data Index: 21136 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6885. Min Range: -2.6885
Max Act: 2.6404. Min Act: -0.1700
Data Index: 1177641 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6885. Min Range: -2.6885
Max Act: 2.6404. Min Act: -0.1700
Data Index: 998551 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6885. Min Range: -2.6885
Max Act: 2.6404. Min Act: -0.1700
Data Index: 1160193 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6885. Min Range: -2.6885
Max Act: 2.6404. Min Act: -0.1700
Data Index: 581231 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6885. Min Range: -2.6885
Max Act: 2.6404. Min Act: -0.1700
Data Index: 366248 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6885. Min Range: -2.6885
Max Act: 2.6404. Min Act: -0.1700
Data Index: 755939 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6885. Min Range: -2.6885
Max Act: 2.6404. Min Act: -0.1700
Data Index: 36413 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6885. Min Range: -2.6885
Max Act: 2.6243. Min Act: -0.1700
Data Index: 167803 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6885. Min Range: -2.6885
Max Act: 2.6404. Min Act: -0.1700
Data Index: 757489 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6885. Min Range: -2.6885
Max Act: 2.6243. Min Act: -0.1700
Data Index: 742155 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6885. Min Range: -2.6885
Max Act: 2.6243. Min Act: -0.1700
Data Index: 56158 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6885. Min Range: -2.6885
Max Act: 2.6243. Min Act: -0.1700
Data Index: 420758 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6885. Min Range: -2.6885
Max Act: 2.6243. Min Act: -0.1700
Data Index: 437523 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19