Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1856 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3531. Min Range: -4.3531
Max Act: 4.3531. Min Act: -0.1700
Data Index: 371654 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3531. Min Range: -4.3531
Max Act: 4.3531. Min Act: -0.1700
Data Index: 498229 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3531. Min Range: -4.3531
Max Act: 4.2281. Min Act: -0.1700
Data Index: 905434 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3531. Min Range: -4.3531
Max Act: 4.1343. Min Act: -0.1700
Data Index: 1480458 (Python Code)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3531. Min Range: -4.3531
Max Act: 4.1343. Min Act: -0.1700
Data Index: 671720 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3531. Min Range: -4.3531
Max Act: 4.0718. Min Act: -0.1700
Data Index: 977666 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3531. Min Range: -4.3531
Max Act: 4.0718. Min Act: -0.1700
Data Index: 1651666 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3531. Min Range: -4.3531
Max Act: 4.0718. Min Act: -0.1700
Data Index: 1388782 (Python Code)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3531. Min Range: -4.3531
Max Act: 4.0718. Min Act: -0.1700
Data Index: 1055199 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3531. Min Range: -4.3531
Max Act: 4.0405. Min Act: -0.1700
Data Index: 1624822 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3531. Min Range: -4.3531
Max Act: 4.0092. Min Act: -0.1700
Data Index: 1449624 (Python Code)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3531. Min Range: -4.3531
Max Act: 3.9780. Min Act: -0.1700
Data Index: 1608800 (Python Code)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3531. Min Range: -4.3531
Max Act: 3.9780. Min Act: -0.1700
Data Index: 1585525 (Python Code)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3531. Min Range: -4.3531
Max Act: 3.9780. Min Act: -0.1700
Data Index: 1652970 (Python Code)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3531. Min Range: -4.3531
Max Act: 4.0405. Min Act: -0.1700
Data Index: 453035 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3531. Min Range: -4.3531
Max Act: 4.0092. Min Act: -0.1700
Data Index: 61165 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3531. Min Range: -4.3531
Max Act: 3.9467. Min Act: -0.1700
Data Index: 1396928 (Python Code)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3531. Min Range: -4.3531
Max Act: 4.0092. Min Act: -0.1700
Data Index: 1487209 (Python Code)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3531. Min Range: -4.3531
Max Act: 3.9780. Min Act: -0.1700
Data Index: 1561411 (Python Code)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3531. Min Range: -4.3531
Max Act: 3.9780. Min Act: -0.1700
Data Index: 441172 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19