Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1853 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.9929. Min Range: -2.9929
Max Act: 2.9929. Min Act: -0.1700
Data Index: 1516096 (Python Code)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9929. Min Range: -2.9929
Max Act: 2.9454. Min Act: -0.1700
Data Index: 354878 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9929. Min Range: -2.9929
Max Act: 2.8979. Min Act: -0.1700
Data Index: 1606888 (Python Code)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9929. Min Range: -2.9929
Max Act: 2.8820. Min Act: -0.1700
Data Index: 1443293 (Python Code)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9929. Min Range: -2.9929
Max Act: 2.8820. Min Act: -0.1700
Data Index: 1555854 (Python Code)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9929. Min Range: -2.9929
Max Act: 2.8503. Min Act: -0.1700
Data Index: 1635222 (Python Code)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9929. Min Range: -2.9929
Max Act: 2.7707. Min Act: -0.1700
Data Index: 1612219 (Python Code)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9929. Min Range: -2.9929
Max Act: 2.7707. Min Act: -0.1700
Data Index: 1391432 (Python Code)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9929. Min Range: -2.9929
Max Act: 2.7228. Min Act: -0.1700
Data Index: 1471090 (Python Code)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9929. Min Range: -2.9929
Max Act: 2.7228. Min Act: -0.1700
Data Index: 1642521 (Python Code)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9929. Min Range: -2.9929
Max Act: 2.7068. Min Act: -0.1700
Data Index: 1491261 (Python Code)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9929. Min Range: -2.9929
Max Act: 2.7228. Min Act: -0.1700
Data Index: 1616051 (Python Code)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9929. Min Range: -2.9929
Max Act: 2.7228. Min Act: -0.1700
Data Index: 1362796 (Python Code)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9929. Min Range: -2.9929
Max Act: 2.7068. Min Act: -0.1700
Data Index: 1369128 (Python Code)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9929. Min Range: -2.9929
Max Act: 2.7228. Min Act: -0.1700
Data Index: 1454465 (Python Code)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9929. Min Range: -2.9929
Max Act: 2.7228. Min Act: -0.1700
Data Index: 1569492 (Python Code)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9929. Min Range: -2.9929
Max Act: 2.7068. Min Act: -0.1700
Data Index: 1531036 (Python Code)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9929. Min Range: -2.9929
Max Act: 2.7068. Min Act: -0.1700
Data Index: 1558039 (Python Code)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9929. Min Range: -2.9929
Max Act: 2.6587. Min Act: -0.1700
Data Index: 1597515 (Python Code)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9929. Min Range: -2.9929
Max Act: 2.6748. Min Act: -0.1700
Data Index: 1475679 (Python Code)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19