Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 380 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.3625. Min Range: -2.3625
Max Act: 2.3625. Min Act: -0.1700
Data Index: 426015 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3625. Min Range: -2.3625
Max Act: 2.2144. Min Act: -0.1700
Data Index: 50278 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3625. Min Range: -2.3625
Max Act: 2.2144. Min Act: -0.1700
Data Index: 665307 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3625. Min Range: -2.3625
Max Act: 2.1812. Min Act: -0.1700
Data Index: 986880 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3625. Min Range: -2.3625
Max Act: 2.1812. Min Act: -0.1700
Data Index: 554003 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3625. Min Range: -2.3625
Max Act: 2.1646. Min Act: -0.1700
Data Index: 512659 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3625. Min Range: -2.3625
Max Act: 2.1978. Min Act: -0.1700
Data Index: 1042537 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3625. Min Range: -2.3625
Max Act: 2.1313. Min Act: -0.1700
Data Index: 178579 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3625. Min Range: -2.3625
Max Act: 2.1646. Min Act: -0.1700
Data Index: 820882 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3625. Min Range: -2.3625
Max Act: 2.1480. Min Act: -0.1700
Data Index: 993882 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3625. Min Range: -2.3625
Max Act: 2.1313. Min Act: -0.1700
Data Index: 1316980 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3625. Min Range: -2.3625
Max Act: 2.1480. Min Act: -0.1700
Data Index: 1304503 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3625. Min Range: -2.3625
Max Act: 2.1480. Min Act: -0.1700
Data Index: 1192929 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3625. Min Range: -2.3625
Max Act: 2.1146. Min Act: -0.1700
Data Index: 133181 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3625. Min Range: -2.3625
Max Act: 2.1313. Min Act: -0.1700
Data Index: 107099 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3625. Min Range: -2.3625
Max Act: 2.1313. Min Act: -0.1700
Data Index: 229413 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3625. Min Range: -2.3625
Max Act: 2.1146. Min Act: -0.1700
Data Index: 231791 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3625. Min Range: -2.3625
Max Act: 2.1146. Min Act: -0.1700
Data Index: 1608176 (Python Code)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3625. Min Range: -2.3625
Max Act: 2.1062. Min Act: -0.1700
Data Index: 603039 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3625. Min Range: -2.3625
Max Act: 2.1146. Min Act: -0.1700
Data Index: 1081568 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19