Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 144 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5789. Min Range: -2.5789
Max Act: 2.5789. Min Act: -0.1700
Data Index: 1473274 (Python Code)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5789. Min Range: -2.5789
Max Act: 2.5628. Min Act: -0.1700
Data Index: 1235199 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5789. Min Range: -2.5789
Max Act: 2.5305. Min Act: -0.1700
Data Index: 1523581 (Python Code)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5789. Min Range: -2.5789
Max Act: 2.5143. Min Act: -0.1700
Data Index: 1513106 (Python Code)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5789. Min Range: -2.5789
Max Act: 2.4982. Min Act: -0.1700
Data Index: 1374980 (Python Code)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5789. Min Range: -2.5789
Max Act: 2.5143. Min Act: -0.1700
Data Index: 1618502 (Python Code)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5789. Min Range: -2.5789
Max Act: 2.4820. Min Act: -0.1699
Data Index: 1427263 (Python Code)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5789. Min Range: -2.5789
Max Act: 2.4820. Min Act: -0.1700
Data Index: 1568148 (Python Code)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5789. Min Range: -2.5789
Max Act: 2.4657. Min Act: -0.1700
Data Index: 1484876 (Python Code)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5789. Min Range: -2.5789
Max Act: 2.4657. Min Act: -0.1700
Data Index: 1422026 (Python Code)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5789. Min Range: -2.5789
Max Act: 2.4495. Min Act: -0.1700
Data Index: 1652999 (Python Code)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5789. Min Range: -2.5789
Max Act: 2.4495. Min Act: -0.1700
Data Index: 285363 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5789. Min Range: -2.5789
Max Act: 2.4495. Min Act: -0.1700
Data Index: 1635044 (Python Code)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5789. Min Range: -2.5789
Max Act: 2.4495. Min Act: -0.1700
Data Index: 1421337 (Python Code)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5789. Min Range: -2.5789
Max Act: 2.4332. Min Act: -0.1700
Data Index: 1425925 (Python Code)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5789. Min Range: -2.5789
Max Act: 2.4332. Min Act: -0.1700
Data Index: 1611899 (Python Code)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5789. Min Range: -2.5789
Max Act: 2.4332. Min Act: -0.1700
Data Index: 1404389 (Python Code)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5789. Min Range: -2.5789
Max Act: 2.4169. Min Act: -0.1700
Data Index: 1571509 (Python Code)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5789. Min Range: -2.5789
Max Act: 2.4006. Min Act: -0.1700
Data Index: 1394294 (Python Code)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5789. Min Range: -2.5789
Max Act: 2.4169. Min Act: -0.1700
Data Index: 1647614 (Python Code)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19