Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1990 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.6206. Min Range: -2.6206
Max Act: 2.6206. Min Act: -0.1700
Data Index: 376827 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6206. Min Range: -2.6206
Max Act: 2.5884. Min Act: -0.1700
Data Index: 981713 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6206. Min Range: -2.6206
Max Act: 2.5884. Min Act: -0.1700
Data Index: 512106 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6206. Min Range: -2.6206
Max Act: 2.5723. Min Act: -0.1700
Data Index: 521352 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6206. Min Range: -2.6206
Max Act: 2.5562. Min Act: -0.1700
Data Index: 1101231 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6206. Min Range: -2.6206
Max Act: 2.5562. Min Act: -0.1700
Data Index: 616241 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6206. Min Range: -2.6206
Max Act: 2.5562. Min Act: -0.1700
Data Index: 991291 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6206. Min Range: -2.6206
Max Act: 2.5562. Min Act: -0.1700
Data Index: 230803 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6206. Min Range: -2.6206
Max Act: 2.5400. Min Act: -0.1700
Data Index: 842272 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6206. Min Range: -2.6206
Max Act: 2.5723. Min Act: -0.1700
Data Index: 1325848 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6206. Min Range: -2.6206
Max Act: 2.5723. Min Act: -0.1700
Data Index: 1324903 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6206. Min Range: -2.6206
Max Act: 2.5562. Min Act: -0.1700
Data Index: 1122302 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6206. Min Range: -2.6206
Max Act: 2.5239. Min Act: -0.1700
Data Index: 841943 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6206. Min Range: -2.6206
Max Act: 2.5239. Min Act: -0.1700
Data Index: 981986 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6206. Min Range: -2.6206
Max Act: 2.5239. Min Act: -0.1700
Data Index: 964743 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6206. Min Range: -2.6206
Max Act: 2.5562. Min Act: -0.1700
Data Index: 427239 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6206. Min Range: -2.6206
Max Act: 2.5077. Min Act: -0.1700
Data Index: 835284 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6206. Min Range: -2.6206
Max Act: 2.5400. Min Act: -0.1700
Data Index: 912216 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6206. Min Range: -2.6206
Max Act: 2.5400. Min Act: -0.1700
Data Index: 126302 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6206. Min Range: -2.6206
Max Act: 2.5400. Min Act: -0.1700
Data Index: 861145 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19