Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 194 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7568. Min Range: -4.7568
Max Act: 4.7568. Min Act: -0.1700
Data Index: 813751 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7568. Min Range: -4.7568
Max Act: 4.6006. Min Act: -0.1700
Data Index: 982423 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7568. Min Range: -4.7568
Max Act: 4.5693. Min Act: -0.1700
Data Index: 78349 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7568. Min Range: -4.7568
Max Act: 4.5381. Min Act: -0.1700
Data Index: 798193 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7568. Min Range: -4.7568
Max Act: 4.5693. Min Act: -0.1700
Data Index: 734632 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7568. Min Range: -4.7568
Max Act: 4.5381. Min Act: -0.1700
Data Index: 816807 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7568. Min Range: -4.7568
Max Act: 4.5068. Min Act: -0.1700
Data Index: 472760 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7568. Min Range: -4.7568
Max Act: 4.4756. Min Act: -0.1700
Data Index: 535995 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7568. Min Range: -4.7568
Max Act: 4.4756. Min Act: -0.1700
Data Index: 429465 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7568. Min Range: -4.7568
Max Act: 4.4756. Min Act: -0.1700
Data Index: 576507 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7568. Min Range: -4.7568
Max Act: 4.4443. Min Act: -0.1700
Data Index: 755370 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7568. Min Range: -4.7568
Max Act: 4.4443. Min Act: -0.1700
Data Index: 955438 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7568. Min Range: -4.7568
Max Act: 4.4756. Min Act: -0.1700
Data Index: 430303 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7568. Min Range: -4.7568
Max Act: 4.4443. Min Act: -0.1700
Data Index: 1235445 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7568. Min Range: -4.7568
Max Act: 4.4443. Min Act: -0.1700
Data Index: 864354 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7568. Min Range: -4.7568
Max Act: 4.4443. Min Act: -0.1700
Data Index: 1112212 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7568. Min Range: -4.7568
Max Act: 4.4443. Min Act: -0.1700
Data Index: 700387 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7568. Min Range: -4.7568
Max Act: 4.4443. Min Act: -0.1700
Data Index: 950728 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7568. Min Range: -4.7568
Max Act: 4.4131. Min Act: -0.1700
Data Index: 104844 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7568. Min Range: -4.7568
Max Act: 4.3818. Min Act: -0.1700
Data Index: 793212 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19