Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 288 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7748. Min Range: -2.7748
Max Act: 2.7748. Min Act: -0.1700
Data Index: 323243 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7748. Min Range: -2.7748
Max Act: 2.6629. Min Act: -0.1700
Data Index: 1264150 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7748. Min Range: -2.7748
Max Act: 2.6629. Min Act: -0.1700
Data Index: 828873 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7748. Min Range: -2.7748
Max Act: 2.6468. Min Act: -0.1700
Data Index: 1146505 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7748. Min Range: -2.7748
Max Act: 2.6308. Min Act: -0.1700
Data Index: 344590 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7748. Min Range: -2.7748
Max Act: 2.6468. Min Act: -0.1700
Data Index: 1206888 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7748. Min Range: -2.7748
Max Act: 2.6308. Min Act: -0.1700
Data Index: 601001 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7748. Min Range: -2.7748
Max Act: 2.6308. Min Act: -0.1700
Data Index: 1236236 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7748. Min Range: -2.7748
Max Act: 2.6308. Min Act: -0.1700
Data Index: 71009 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7748. Min Range: -2.7748
Max Act: 2.6308. Min Act: -0.1700
Data Index: 1300496 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7748. Min Range: -2.7748
Max Act: 2.6147. Min Act: -0.1700
Data Index: 943103 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7748. Min Range: -2.7748
Max Act: 2.5986. Min Act: -0.1700
Data Index: 926460 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7748. Min Range: -2.7748
Max Act: 2.5825. Min Act: -0.1700
Data Index: 634642 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7748. Min Range: -2.7748
Max Act: 2.5825. Min Act: -0.1700
Data Index: 703127 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7748. Min Range: -2.7748
Max Act: 2.5503. Min Act: -0.1700
Data Index: 346255 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7748. Min Range: -2.7748
Max Act: 2.5664. Min Act: -0.1700
Data Index: 354954 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7748. Min Range: -2.7748
Max Act: 2.5341. Min Act: -0.1700
Data Index: 1111277 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7748. Min Range: -2.7748
Max Act: 2.5179. Min Act: -0.1700
Data Index: 223042 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7748. Min Range: -2.7748
Max Act: 2.5341. Min Act: -0.1700
Data Index: 291504 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7748. Min Range: -2.7748
Max Act: 2.5503. Min Act: -0.1700
Data Index: 270088 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19