Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2040 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8333. Min Range: -4.8333
Max Act: 4.8333. Min Act: -0.1700
Data Index: 105053 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8333. Min Range: -4.8333
Max Act: 4.7083. Min Act: -0.1700
Data Index: 849151 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8333. Min Range: -4.8333
Max Act: 4.6771. Min Act: -0.1700
Data Index: 427672 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8333. Min Range: -4.8333
Max Act: 4.6771. Min Act: -0.1700
Data Index: 1226278 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8333. Min Range: -4.8333
Max Act: 4.7083. Min Act: -0.1700
Data Index: 61426 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8333. Min Range: -4.8333
Max Act: 4.7083. Min Act: -0.1700
Data Index: 140988 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8333. Min Range: -4.8333
Max Act: 4.6458. Min Act: -0.1700
Data Index: 555193 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8333. Min Range: -4.8333
Max Act: 4.7083. Min Act: -0.1700
Data Index: 551677 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8333. Min Range: -4.8333
Max Act: 4.6146. Min Act: -0.1700
Data Index: 698173 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8333. Min Range: -4.8333
Max Act: 4.6771. Min Act: -0.1700
Data Index: 166916 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8333. Min Range: -4.8333
Max Act: 4.5833. Min Act: -0.1700
Data Index: 562119 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8333. Min Range: -4.8333
Max Act: 4.6458. Min Act: -0.1700
Data Index: 969249 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8333. Min Range: -4.8333
Max Act: 4.6146. Min Act: -0.1700
Data Index: 17906 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8333. Min Range: -4.8333
Max Act: 4.6771. Min Act: -0.1700
Data Index: 1256746 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8333. Min Range: -4.8333
Max Act: 4.6771. Min Act: -0.1700
Data Index: 1267853 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8333. Min Range: -4.8333
Max Act: 4.6458. Min Act: -0.1700
Data Index: 31067 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8333. Min Range: -4.8333
Max Act: 4.6146. Min Act: -0.1700
Data Index: 479548 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8333. Min Range: -4.8333
Max Act: 4.6146. Min Act: -0.1700
Data Index: 774027 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8333. Min Range: -4.8333
Max Act: 4.6771. Min Act: -0.1700
Data Index: 797785 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8333. Min Range: -4.8333
Max Act: 4.5833. Min Act: -0.1700
Data Index: 1079247 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19