Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2006 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 1.8855. Min Range: -1.8855
Max Act: 1.8855. Min Act: -0.1700
Data Index: 81837 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8855. Min Range: -1.8855
Max Act: 1.8684. Min Act: -0.1700
Data Index: 722427 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8855. Min Range: -1.8855
Max Act: 1.8513. Min Act: -0.1700
Data Index: 236517 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8855. Min Range: -1.8855
Max Act: 1.8513. Min Act: -0.1700
Data Index: 739662 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8855. Min Range: -1.8855
Max Act: 1.8342. Min Act: -0.1700
Data Index: 799587 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8855. Min Range: -1.8855
Max Act: 1.8342. Min Act: -0.1700
Data Index: 2183 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8855. Min Range: -1.8855
Max Act: 1.8171. Min Act: -0.1700
Data Index: 1020496 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8855. Min Range: -1.8855
Max Act: 1.8171. Min Act: -0.1700
Data Index: 925305 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8855. Min Range: -1.8855
Max Act: 1.8171. Min Act: -0.1700
Data Index: 174791 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8855. Min Range: -1.8855
Max Act: 1.7999. Min Act: -0.1700
Data Index: 493657 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8855. Min Range: -1.8855
Max Act: 1.7999. Min Act: -0.1700
Data Index: 1245100 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8855. Min Range: -1.8855
Max Act: 1.7827. Min Act: -0.1700
Data Index: 959254 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8855. Min Range: -1.8855
Max Act: 1.7999. Min Act: -0.1700
Data Index: 538211 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8855. Min Range: -1.8855
Max Act: 1.7654. Min Act: -0.1700
Data Index: 1156782 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8855. Min Range: -1.8855
Max Act: 1.7827. Min Act: -0.1700
Data Index: 678593 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8855. Min Range: -1.8855
Max Act: 1.7654. Min Act: -0.1700
Data Index: 688697 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8855. Min Range: -1.8855
Max Act: 1.7827. Min Act: -0.1700
Data Index: 53002 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8855. Min Range: -1.8855
Max Act: 1.7827. Min Act: -0.1700
Data Index: 359634 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8855. Min Range: -1.8855
Max Act: 1.7827. Min Act: -0.1700
Data Index: 739612 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8855. Min Range: -1.8855
Max Act: 1.7827. Min Act: -0.1700
Data Index: 869557 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19