Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2023 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1161. Min Range: -4.1161
Max Act: 4.1161. Min Act: -0.1700
Data Index: 788001 (C4 (Web Text))
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1161. Min Range: -4.1161
Max Act: 4.0535. Min Act: -0.1700
Data Index: 702888 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1161. Min Range: -4.1161
Max Act: 4.1161. Min Act: -0.1700
Data Index: 77423 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1161. Min Range: -4.1161
Max Act: 4.0848. Min Act: -0.1700
Data Index: 193072 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1161. Min Range: -4.1161
Max Act: 4.0223. Min Act: -0.1700
Data Index: 548693 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1161. Min Range: -4.1161
Max Act: 4.0535. Min Act: -0.1700
Data Index: 453095 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1161. Min Range: -4.1161
Max Act: 4.0223. Min Act: -0.1700
Data Index: 786715 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1161. Min Range: -4.1161
Max Act: 4.0535. Min Act: -0.1700
Data Index: 286855 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1161. Min Range: -4.1161
Max Act: 3.9597. Min Act: -0.1700
Data Index: 243495 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1161. Min Range: -4.1161
Max Act: 3.9597. Min Act: -0.1700
Data Index: 1242001 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1161. Min Range: -4.1161
Max Act: 3.9285. Min Act: -0.1700
Data Index: 121059 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1161. Min Range: -4.1161
Max Act: 3.9285. Min Act: -0.1700
Data Index: 345769 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1161. Min Range: -4.1161
Max Act: 4.0535. Min Act: -0.1700
Data Index: 1213432 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1161. Min Range: -4.1161
Max Act: 3.9285. Min Act: -0.1700
Data Index: 487995 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1161. Min Range: -4.1161
Max Act: 3.9285. Min Act: -0.1700
Data Index: 356152 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1161. Min Range: -4.1161
Max Act: 3.9597. Min Act: -0.1700
Data Index: 868083 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1161. Min Range: -4.1161
Max Act: 3.9910. Min Act: -0.1700
Data Index: 441050 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1161. Min Range: -4.1161
Max Act: 3.9597. Min Act: -0.1700
Data Index: 538299 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1161. Min Range: -4.1161
Max Act: 3.9597. Min Act: -0.1700
Data Index: 1296044 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1161. Min Range: -4.1161
Max Act: 3.9285. Min Act: -0.1700
Data Index: 762733 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19