Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1592 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0862. Min Range: -3.0862
Max Act: 3.0862. Min Act: -0.1700
Data Index: 1614676 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0862. Min Range: -3.0862
Max Act: 3.0388. Min Act: -0.1700
Data Index: 1488507 (Python Code)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0862. Min Range: -3.0862
Max Act: 3.0072. Min Act: -0.1700
Data Index: 1599830 (Python Code)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0862. Min Range: -3.0862
Max Act: 3.0072. Min Act: -0.1700
Data Index: 1623455 (Python Code)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0862. Min Range: -3.0862
Max Act: 3.0072. Min Act: -0.1700
Data Index: 1378427 (Python Code)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0862. Min Range: -3.0862
Max Act: 2.9914. Min Act: -0.1700
Data Index: 1561394 (Python Code)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0862. Min Range: -3.0862
Max Act: 2.9914. Min Act: -0.1700
Data Index: 1622680 (Python Code)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0862. Min Range: -3.0862
Max Act: 2.9756. Min Act: -0.1700
Data Index: 1524871 (Python Code)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0862. Min Range: -3.0862
Max Act: 2.9756. Min Act: -0.1700
Data Index: 1591136 (Python Code)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0862. Min Range: -3.0862
Max Act: 2.9598. Min Act: -0.1700
Data Index: 1617884 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0862. Min Range: -3.0862
Max Act: 2.9440. Min Act: -0.1700
Data Index: 1366235 (Python Code)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0862. Min Range: -3.0862
Max Act: 2.9756. Min Act: -0.1700
Data Index: 1571591 (Python Code)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0862. Min Range: -3.0862
Max Act: 2.9756. Min Act: -0.1700
Data Index: 1621670 (Python Code)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0862. Min Range: -3.0862
Max Act: 2.9598. Min Act: -0.1700
Data Index: 1614001 (Python Code)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0862. Min Range: -3.0862
Max Act: 2.9281. Min Act: -0.1700
Data Index: 732543 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0862. Min Range: -3.0862
Max Act: 2.9281. Min Act: -0.1700
Data Index: 1523336 (Python Code)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0862. Min Range: -3.0862
Max Act: 2.9440. Min Act: -0.1700
Data Index: 1428683 (Python Code)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0862. Min Range: -3.0862
Max Act: 2.9440. Min Act: -0.1700
Data Index: 1632508 (Python Code)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0862. Min Range: -3.0862
Max Act: 2.9281. Min Act: -0.1700
Data Index: 1411696 (Python Code)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0862. Min Range: -3.0862
Max Act: 2.9440. Min Act: -0.1700
Data Index: 1634949 (Python Code)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19