Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1369 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8410. Min Range: -4.8410
Max Act: 4.8410. Min Act: -0.1700
Data Index: 1228827 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8410. Min Range: -4.8410
Max Act: 4.7472. Min Act: -0.1700
Data Index: 456033 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8410. Min Range: -4.8410
Max Act: 4.6535. Min Act: -0.1700
Data Index: 184204 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8410. Min Range: -4.8410
Max Act: 4.6847. Min Act: -0.1700
Data Index: 303835 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8410. Min Range: -4.8410
Max Act: 4.7160. Min Act: -0.1700
Data Index: 127370 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8410. Min Range: -4.8410
Max Act: 4.6535. Min Act: -0.1700
Data Index: 865135 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8410. Min Range: -4.8410
Max Act: 4.5284. Min Act: -0.1700
Data Index: 999517 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8410. Min Range: -4.8410
Max Act: 4.5597. Min Act: -0.1700
Data Index: 630217 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8410. Min Range: -4.8410
Max Act: 4.5597. Min Act: -0.1700
Data Index: 313393 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8410. Min Range: -4.8410
Max Act: 4.4659. Min Act: -0.1700
Data Index: 295489 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8410. Min Range: -4.8410
Max Act: 4.5284. Min Act: -0.1700
Data Index: 869027 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8410. Min Range: -4.8410
Max Act: 4.5284. Min Act: -0.1700
Data Index: 888160 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8410. Min Range: -4.8410
Max Act: 4.4972. Min Act: -0.1700
Data Index: 932032 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8410. Min Range: -4.8410
Max Act: 4.5284. Min Act: -0.1700
Data Index: 863863 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8410. Min Range: -4.8410
Max Act: 4.5284. Min Act: -0.1700
Data Index: 90916 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8410. Min Range: -4.8410
Max Act: 4.4659. Min Act: -0.1700
Data Index: 541718 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8410. Min Range: -4.8410
Max Act: 4.4972. Min Act: -0.1700
Data Index: 392072 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8410. Min Range: -4.8410
Max Act: 4.4659. Min Act: -0.1700
Data Index: 1439 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8410. Min Range: -4.8410
Max Act: 4.4972. Min Act: -0.1700
Data Index: 593866 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8410. Min Range: -4.8410
Max Act: 4.4347. Min Act: -0.1700
Data Index: 947793 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19