Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1531 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.2730. Min Range: -2.2730
Max Act: 2.2730. Min Act: -0.1700
Data Index: 255981 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2730. Min Range: -2.2730
Max Act: 2.2400. Min Act: -0.1700
Data Index: 1309247 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2730. Min Range: -2.2730
Max Act: 2.2400. Min Act: -0.1700
Data Index: 390953 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2730. Min Range: -2.2730
Max Act: 2.2069. Min Act: -0.1700
Data Index: 543129 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2730. Min Range: -2.2730
Max Act: 2.1903. Min Act: -0.1700
Data Index: 1245124 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2730. Min Range: -2.2730
Max Act: 2.2069. Min Act: -0.1700
Data Index: 326859 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2730. Min Range: -2.2730
Max Act: 2.1903. Min Act: -0.1700
Data Index: 609643 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2730. Min Range: -2.2730
Max Act: 2.1737. Min Act: -0.1700
Data Index: 377679 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2730. Min Range: -2.2730
Max Act: 2.1903. Min Act: -0.1700
Data Index: 430149 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2730. Min Range: -2.2730
Max Act: 2.1737. Min Act: -0.1700
Data Index: 332327 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2730. Min Range: -2.2730
Max Act: 2.1737. Min Act: -0.1700
Data Index: 1143870 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2730. Min Range: -2.2730
Max Act: 2.1903. Min Act: -0.1700
Data Index: 1090238 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2730. Min Range: -2.2730
Max Act: 2.1737. Min Act: -0.1700
Data Index: 162065 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2730. Min Range: -2.2730
Max Act: 2.1571. Min Act: -0.1700
Data Index: 53649 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2730. Min Range: -2.2730
Max Act: 2.1571. Min Act: -0.1700
Data Index: 1310226 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2730. Min Range: -2.2730
Max Act: 2.1737. Min Act: -0.1700
Data Index: 607085 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2730. Min Range: -2.2730
Max Act: 2.1737. Min Act: -0.1700
Data Index: 620164 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2730. Min Range: -2.2730
Max Act: 2.1571. Min Act: -0.1700
Data Index: 955069 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2730. Min Range: -2.2730
Max Act: 2.1404. Min Act: -0.1700
Data Index: 410783 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2730. Min Range: -2.2730
Max Act: 2.1571. Min Act: -0.1700
Data Index: 477393 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19