Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1139 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8060. Min Range: -2.8060
Max Act: 2.8060. Min Act: -0.1700
Data Index: 327862 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8060. Min Range: -2.8060
Max Act: 2.8060. Min Act: -0.1700
Data Index: 276381 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8060. Min Range: -2.8060
Max Act: 2.7582. Min Act: -0.1700
Data Index: 280500 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8060. Min Range: -2.8060
Max Act: 2.7423. Min Act: -0.1700
Data Index: 668390 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8060. Min Range: -2.8060
Max Act: 2.7263. Min Act: -0.1700
Data Index: 366039 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8060. Min Range: -2.8060
Max Act: 2.7263. Min Act: -0.1700
Data Index: 253059 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8060. Min Range: -2.8060
Max Act: 2.7423. Min Act: -0.1700
Data Index: 628606 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8060. Min Range: -2.8060
Max Act: 2.6943. Min Act: -0.1700
Data Index: 103612 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8060. Min Range: -2.8060
Max Act: 2.6783. Min Act: -0.1700
Data Index: 12250 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8060. Min Range: -2.8060
Max Act: 2.6783. Min Act: -0.1700
Data Index: 280067 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8060. Min Range: -2.8060
Max Act: 2.6622. Min Act: -0.1700
Data Index: 226665 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8060. Min Range: -2.8060
Max Act: 2.6783. Min Act: -0.1700
Data Index: 1145158 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8060. Min Range: -2.8060
Max Act: 2.6462. Min Act: -0.1700
Data Index: 953524 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8060. Min Range: -2.8060
Max Act: 2.6622. Min Act: -0.1700
Data Index: 418290 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8060. Min Range: -2.8060
Max Act: 2.6462. Min Act: -0.1700
Data Index: 153865 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8060. Min Range: -2.8060
Max Act: 2.6301. Min Act: -0.1700
Data Index: 318750 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8060. Min Range: -2.8060
Max Act: 2.6301. Min Act: -0.1700
Data Index: 278757 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8060. Min Range: -2.8060
Max Act: 2.6301. Min Act: -0.1700
Data Index: 3751 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8060. Min Range: -2.8060
Max Act: 2.6141. Min Act: -0.1700
Data Index: 712787 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8060. Min Range: -2.8060
Max Act: 2.6301. Min Act: -0.1700
Data Index: 701111 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19