Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 298 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8417. Min Range: -2.8417
Max Act: 2.8417. Min Act: -0.1700
Data Index: 1175735 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8417. Min Range: -2.8417
Max Act: 2.7940. Min Act: -0.1700
Data Index: 369174 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8417. Min Range: -2.8417
Max Act: 2.6822. Min Act: -0.1700
Data Index: 295893 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8417. Min Range: -2.8417
Max Act: 2.6340. Min Act: -0.1700
Data Index: 707609 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8417. Min Range: -2.8417
Max Act: 2.5858. Min Act: -0.1700
Data Index: 16861 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8417. Min Range: -2.8417
Max Act: 2.5374. Min Act: -0.1700
Data Index: 1109673 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8417. Min Range: -2.8417
Max Act: 2.5051. Min Act: -0.1700
Data Index: 33099 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8417. Min Range: -2.8417
Max Act: 2.5051. Min Act: -0.1700
Data Index: 1225191 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8417. Min Range: -2.8417
Max Act: 2.5051. Min Act: -0.1700
Data Index: 422957 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8417. Min Range: -2.8417
Max Act: 2.4726. Min Act: -0.1700
Data Index: 206626 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8417. Min Range: -2.8417
Max Act: 2.4564. Min Act: -0.1700
Data Index: 540173 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8417. Min Range: -2.8417
Max Act: 2.4726. Min Act: -0.1700
Data Index: 1355086 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8417. Min Range: -2.8417
Max Act: 2.4402. Min Act: -0.1700
Data Index: 385923 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8417. Min Range: -2.8417
Max Act: 2.4402. Min Act: -0.1700
Data Index: 802069 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8417. Min Range: -2.8417
Max Act: 2.4402. Min Act: -0.1700
Data Index: 723171 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8417. Min Range: -2.8417
Max Act: 2.4402. Min Act: -0.1700
Data Index: 1327020 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8417. Min Range: -2.8417
Max Act: 2.4402. Min Act: -0.1700
Data Index: 179141 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8417. Min Range: -2.8417
Max Act: 2.4402. Min Act: -0.1700
Data Index: 251585 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8417. Min Range: -2.8417
Max Act: 2.4239. Min Act: -0.1700
Data Index: 541131 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8417. Min Range: -2.8417
Max Act: 2.4239. Min Act: -0.1700
Data Index: 852281 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19