Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1957 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0360. Min Range: -3.0360
Max Act: 3.0360. Min Act: -0.1700
Data Index: 843874 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.9728. Min Act: -0.1700
Data Index: 298704 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.9253. Min Act: -0.1700
Data Index: 1003486 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.9253. Min Act: -0.1700
Data Index: 363324 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.9253. Min Act: -0.1700
Data Index: 792212 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.9253. Min Act: -0.1700
Data Index: 669622 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.9094. Min Act: -0.1700
Data Index: 370655 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.9094. Min Act: -0.1700
Data Index: 783219 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.9094. Min Act: -0.1700
Data Index: 292340 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.8618. Min Act: -0.1700
Data Index: 555263 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.8936. Min Act: -0.1700
Data Index: 687239 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.8936. Min Act: -0.1700
Data Index: 87123 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.8936. Min Act: -0.1700
Data Index: 193141 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.8936. Min Act: -0.1700
Data Index: 272468 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.8777. Min Act: -0.1700
Data Index: 147322 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.8777. Min Act: -0.1700
Data Index: 420329 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.8618. Min Act: -0.1700
Data Index: 271103 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.8777. Min Act: -0.1700
Data Index: 509851 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.8777. Min Act: -0.1700
Data Index: 642842 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0360. Min Range: -3.0360
Max Act: 2.8777. Min Act: -0.1700
Data Index: 169733 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19