Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1012 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.6472. Min Range: -2.6472
Max Act: 2.6472. Min Act: -0.1700
Data Index: 3309 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6472. Min Range: -2.6472
Max Act: 2.6151. Min Act: -0.1700
Data Index: 460929 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6472. Min Range: -2.6472
Max Act: 2.5829. Min Act: -0.1700
Data Index: 455426 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6472. Min Range: -2.6472
Max Act: 2.5990. Min Act: -0.1700
Data Index: 1319401 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6472. Min Range: -2.6472
Max Act: 2.5668. Min Act: -0.1700
Data Index: 1161589 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6472. Min Range: -2.6472
Max Act: 2.5506. Min Act: -0.1700
Data Index: 1525926 (Python Code)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6472. Min Range: -2.6472
Max Act: 2.5345. Min Act: -0.1700
Data Index: 1604111 (Python Code)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6472. Min Range: -2.6472
Max Act: 2.5506. Min Act: -0.1700
Data Index: 233170 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6472. Min Range: -2.6472
Max Act: 2.5345. Min Act: -0.1700
Data Index: 99943 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6472. Min Range: -2.6472
Max Act: 2.5183. Min Act: -0.1700
Data Index: 814146 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6472. Min Range: -2.6472
Max Act: 2.5345. Min Act: -0.1700
Data Index: 1408755 (Python Code)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6472. Min Range: -2.6472
Max Act: 2.5345. Min Act: -0.1700
Data Index: 1494757 (Python Code)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6472. Min Range: -2.6472
Max Act: 2.5345. Min Act: -0.1700
Data Index: 1609959 (Python Code)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6472. Min Range: -2.6472
Max Act: 2.5183. Min Act: -0.1700
Data Index: 284047 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6472. Min Range: -2.6472
Max Act: 2.5183. Min Act: -0.1700
Data Index: 1593708 (Python Code)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6472. Min Range: -2.6472
Max Act: 2.5183. Min Act: -0.1700
Data Index: 1402455 (Python Code)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6472. Min Range: -2.6472
Max Act: 2.5183. Min Act: -0.1700
Data Index: 1580742 (Python Code)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6472. Min Range: -2.6472
Max Act: 2.5183. Min Act: -0.1700
Data Index: 1633689 (Python Code)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6472. Min Range: -2.6472
Max Act: 2.5183. Min Act: -0.1700
Data Index: 1405035 (Python Code)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6472. Min Range: -2.6472
Max Act: 2.5021. Min Act: -0.1700
Data Index: 1627298 (Python Code)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19