Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2002 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.0289. Min Range: -4.0289
Max Act: 3.9664. Min Act: -0.1700
Data Index: 543008 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0289. Min Range: -4.0289
Max Act: 4.0289. Min Act: -0.1700
Data Index: 1315342 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0289. Min Range: -4.0289
Max Act: 4.0289. Min Act: -0.1700
Data Index: 105464 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0289. Min Range: -4.0289
Max Act: 3.9351. Min Act: -0.1700
Data Index: 476926 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0289. Min Range: -4.0289
Max Act: 3.9351. Min Act: -0.1700
Data Index: 1271235 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0289. Min Range: -4.0289
Max Act: 3.9351. Min Act: -0.1700
Data Index: 1193938 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0289. Min Range: -4.0289
Max Act: 3.9664. Min Act: -0.1700
Data Index: 1002694 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0289. Min Range: -4.0289
Max Act: 3.9038. Min Act: -0.1700
Data Index: 491463 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0289. Min Range: -4.0289
Max Act: 3.9038. Min Act: -0.1700
Data Index: 993029 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0289. Min Range: -4.0289
Max Act: 3.9038. Min Act: -0.1700
Data Index: 266412 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0289. Min Range: -4.0289
Max Act: 3.8726. Min Act: -0.1700
Data Index: 874562 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0289. Min Range: -4.0289
Max Act: 3.8726. Min Act: -0.1700
Data Index: 1291430 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0289. Min Range: -4.0289
Max Act: 3.8726. Min Act: -0.1700
Data Index: 810377 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0289. Min Range: -4.0289
Max Act: 3.8726. Min Act: -0.1700
Data Index: 1035745 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0289. Min Range: -4.0289
Max Act: 3.8726. Min Act: -0.1700
Data Index: 295430 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0289. Min Range: -4.0289
Max Act: 3.8413. Min Act: -0.1700
Data Index: 1045457 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0289. Min Range: -4.0289
Max Act: 3.8100. Min Act: -0.1700
Data Index: 1101732 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0289. Min Range: -4.0289
Max Act: 3.8413. Min Act: -0.1700
Data Index: 573380 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0289. Min Range: -4.0289
Max Act: 3.8413. Min Act: -0.1700
Data Index: 324264 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0289. Min Range: -4.0289
Max Act: 3.8413. Min Act: -0.1700
Data Index: 923933 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19