Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1999 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.1422. Min Range: -4.1422
Max Act: 4.1422. Min Act: -0.1700
Data Index: 1523793 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1422. Min Range: -4.1422
Max Act: 4.1266. Min Act: -0.1700
Data Index: 1461599 (Python Code)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1422. Min Range: -4.1422
Max Act: 4.0797. Min Act: -0.1700
Data Index: 365558 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1422. Min Range: -4.1422
Max Act: 4.0484. Min Act: -0.1700
Data Index: 412102 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1422. Min Range: -4.1422
Max Act: 3.9859. Min Act: -0.1700
Data Index: 337488 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1422. Min Range: -4.1422
Max Act: 3.9546. Min Act: -0.1700
Data Index: 51147 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1422. Min Range: -4.1422
Max Act: 3.9390. Min Act: -0.1700
Data Index: 176449 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1422. Min Range: -4.1422
Max Act: 3.9077. Min Act: -0.1700
Data Index: 22349 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1422. Min Range: -4.1422
Max Act: 3.9234. Min Act: -0.1700
Data Index: 421010 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1422. Min Range: -4.1422
Max Act: 3.9077. Min Act: -0.1700
Data Index: 89547 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1422. Min Range: -4.1422
Max Act: 3.9234. Min Act: -0.1700
Data Index: 593135 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1422. Min Range: -4.1422
Max Act: 3.8608. Min Act: -0.1700
Data Index: 1376304 (Python Code)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1422. Min Range: -4.1422
Max Act: 3.8921. Min Act: -0.1700
Data Index: 822735 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1422. Min Range: -4.1422
Max Act: 3.8921. Min Act: -0.1700
Data Index: 893115 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1422. Min Range: -4.1422
Max Act: 3.8608. Min Act: -0.1700
Data Index: 994237 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1422. Min Range: -4.1422
Max Act: 3.8608. Min Act: -0.1700
Data Index: 1016766 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1422. Min Range: -4.1422
Max Act: 3.9077. Min Act: -0.1700
Data Index: 366900 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1422. Min Range: -4.1422
Max Act: 3.8764. Min Act: -0.1700
Data Index: 197550 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1422. Min Range: -4.1422
Max Act: 3.8764. Min Act: -0.1700
Data Index: 771123 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1422. Min Range: -4.1422
Max Act: 3.8452. Min Act: -0.1700
Data Index: 1086455 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19