Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1956 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8860. Min Range: -2.8860
Max Act: 2.8860. Min Act: -0.1700
Data Index: 9734 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8860. Min Range: -2.8860
Max Act: 2.8701. Min Act: -0.1700
Data Index: 728842 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8860. Min Range: -2.8860
Max Act: 2.8383. Min Act: -0.1700
Data Index: 1034406 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8860. Min Range: -2.8860
Max Act: 2.8383. Min Act: -0.1700
Data Index: 1083304 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8860. Min Range: -2.8860
Max Act: 2.8383. Min Act: -0.1700
Data Index: 752592 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8860. Min Range: -2.8860
Max Act: 2.8224. Min Act: -0.1700
Data Index: 703925 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8860. Min Range: -2.8860
Max Act: 2.8224. Min Act: -0.1700
Data Index: 997293 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8860. Min Range: -2.8860
Max Act: 2.8224. Min Act: -0.1700
Data Index: 456270 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8860. Min Range: -2.8860
Max Act: 2.8224. Min Act: -0.1700
Data Index: 540332 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8860. Min Range: -2.8860
Max Act: 2.8224. Min Act: -0.1700
Data Index: 824385 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8860. Min Range: -2.8860
Max Act: 2.8224. Min Act: -0.1700
Data Index: 752676 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8860. Min Range: -2.8860
Max Act: 2.7906. Min Act: -0.1700
Data Index: 1006935 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8860. Min Range: -2.8860
Max Act: 2.8065. Min Act: -0.1700
Data Index: 56177 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8860. Min Range: -2.8860
Max Act: 2.8065. Min Act: -0.1700
Data Index: 131933 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8860. Min Range: -2.8860
Max Act: 2.8065. Min Act: -0.1700
Data Index: 1032485 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8860. Min Range: -2.8860
Max Act: 2.8065. Min Act: -0.1700
Data Index: 808167 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8860. Min Range: -2.8860
Max Act: 2.8065. Min Act: -0.1700
Data Index: 456034 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8860. Min Range: -2.8860
Max Act: 2.8065. Min Act: -0.1700
Data Index: 358463 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8860. Min Range: -2.8860
Max Act: 2.8224. Min Act: -0.1700
Data Index: 652420 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8860. Min Range: -2.8860
Max Act: 2.8065. Min Act: -0.1700
Data Index: 797328 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19