Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 713 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.2327. Min Range: -4.2327
Max Act: 4.2327. Min Act: -0.1700
Data Index: 110423 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2327. Min Range: -4.2327
Max Act: 4.2015. Min Act: -0.1700
Data Index: 214260 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2327. Min Range: -4.2327
Max Act: 4.1077. Min Act: -0.1700
Data Index: 101694 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2327. Min Range: -4.2327
Max Act: 4.1077. Min Act: -0.1700
Data Index: 423544 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2327. Min Range: -4.2327
Max Act: 4.1077. Min Act: -0.1700
Data Index: 355432 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2327. Min Range: -4.2327
Max Act: 4.0452. Min Act: -0.1700
Data Index: 1193623 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2327. Min Range: -4.2327
Max Act: 4.1390. Min Act: -0.1700
Data Index: 636268 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2327. Min Range: -4.2327
Max Act: 4.0764. Min Act: -0.1700
Data Index: 42036 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2327. Min Range: -4.2327
Max Act: 4.0764. Min Act: -0.1700
Data Index: 995456 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2327. Min Range: -4.2327
Max Act: 4.1077. Min Act: -0.1700
Data Index: 708668 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2327. Min Range: -4.2327
Max Act: 4.0764. Min Act: -0.1700
Data Index: 943854 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2327. Min Range: -4.2327
Max Act: 4.0764. Min Act: -0.1700
Data Index: 62088 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2327. Min Range: -4.2327
Max Act: 4.0452. Min Act: -0.1700
Data Index: 891641 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2327. Min Range: -4.2327
Max Act: 4.0452. Min Act: -0.1700
Data Index: 557253 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2327. Min Range: -4.2327
Max Act: 4.1077. Min Act: -0.1700
Data Index: 1003261 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2327. Min Range: -4.2327
Max Act: 4.0139. Min Act: -0.1700
Data Index: 162312 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2327. Min Range: -4.2327
Max Act: 3.9826. Min Act: -0.1700
Data Index: 555582 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2327. Min Range: -4.2327
Max Act: 4.0452. Min Act: -0.1700
Data Index: 808826 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2327. Min Range: -4.2327
Max Act: 3.9826. Min Act: -0.1700
Data Index: 501408 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2327. Min Range: -4.2327
Max Act: 3.9201. Min Act: -0.1700
Data Index: 259177 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19