Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1978 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.6809. Min Range: -2.6809
Max Act: 2.6809. Min Act: -0.1700
Data Index: 135700 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6809. Min Range: -2.6809
Max Act: 2.6489. Min Act: -0.1700
Data Index: 1579531 (Python Code)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6809. Min Range: -2.6809
Max Act: 2.6489. Min Act: -0.1700
Data Index: 928841 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6809. Min Range: -2.6809
Max Act: 2.6649. Min Act: -0.1700
Data Index: 700355 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6809. Min Range: -2.6809
Max Act: 2.6167. Min Act: -0.1700
Data Index: 188355 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6809. Min Range: -2.6809
Max Act: 2.6328. Min Act: -0.1700
Data Index: 285676 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6809. Min Range: -2.6809
Max Act: 2.6167. Min Act: -0.1700
Data Index: 181018 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6809. Min Range: -2.6809
Max Act: 2.6006. Min Act: -0.1700
Data Index: 980855 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6809. Min Range: -2.6809
Max Act: 2.5845. Min Act: -0.1700
Data Index: 1511337 (Python Code)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6809. Min Range: -2.6809
Max Act: 2.5845. Min Act: -0.1700
Data Index: 1214247 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6809. Min Range: -2.6809
Max Act: 2.5684. Min Act: -0.1700
Data Index: 275363 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6809. Min Range: -2.6809
Max Act: 2.5845. Min Act: -0.1700
Data Index: 1153121 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6809. Min Range: -2.6809
Max Act: 2.5845. Min Act: -0.1700
Data Index: 287082 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6809. Min Range: -2.6809
Max Act: 2.5845. Min Act: -0.1700
Data Index: 19215 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6809. Min Range: -2.6809
Max Act: 2.5684. Min Act: -0.1700
Data Index: 1002754 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6809. Min Range: -2.6809
Max Act: 2.5523. Min Act: -0.1700
Data Index: 624223 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6809. Min Range: -2.6809
Max Act: 2.5684. Min Act: -0.1700
Data Index: 894330 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6809. Min Range: -2.6809
Max Act: 2.5523. Min Act: -0.1700
Data Index: 893137 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6809. Min Range: -2.6809
Max Act: 2.5523. Min Act: -0.1700
Data Index: 576791 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6809. Min Range: -2.6809
Max Act: 2.5684. Min Act: -0.1700
Data Index: 712368 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19