Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 418 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9658. Min Range: -2.9658
Max Act: 2.9658. Min Act: -0.1700
Data Index: 896000 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9658. Min Range: -2.9658
Max Act: 2.9341. Min Act: -0.1700
Data Index: 369387 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9658. Min Range: -2.9658
Max Act: 2.9341. Min Act: -0.1700
Data Index: 678442 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9658. Min Range: -2.9658
Max Act: 2.8548. Min Act: -0.1700
Data Index: 197168 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9658. Min Range: -2.9658
Max Act: 2.8230. Min Act: -0.1700
Data Index: 833788 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9658. Min Range: -2.9658
Max Act: 2.8548. Min Act: -0.1700
Data Index: 433441 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9658. Min Range: -2.9658
Max Act: 2.8230. Min Act: -0.1700
Data Index: 43820 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9658. Min Range: -2.9658
Max Act: 2.8071. Min Act: -0.1700
Data Index: 160153 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9658. Min Range: -2.9658
Max Act: 2.8071. Min Act: -0.1700
Data Index: 1038729 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9658. Min Range: -2.9658
Max Act: 2.8071. Min Act: -0.1700
Data Index: 345503 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9658. Min Range: -2.9658
Max Act: 2.7911. Min Act: -0.1700
Data Index: 187303 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9658. Min Range: -2.9658
Max Act: 2.8071. Min Act: -0.1700
Data Index: 131281 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9658. Min Range: -2.9658
Max Act: 2.8071. Min Act: -0.1700
Data Index: 32925 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9658. Min Range: -2.9658
Max Act: 2.7911. Min Act: -0.1700
Data Index: 404604 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9658. Min Range: -2.9658
Max Act: 2.7911. Min Act: -0.1700
Data Index: 600971 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9658. Min Range: -2.9658
Max Act: 2.7752. Min Act: -0.1700
Data Index: 956237 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9658. Min Range: -2.9658
Max Act: 2.7752. Min Act: -0.1700
Data Index: 350605 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9658. Min Range: -2.9658
Max Act: 2.7752. Min Act: -0.1700
Data Index: 196086 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9658. Min Range: -2.9658
Max Act: 2.7752. Min Act: -0.1700
Data Index: 1153071 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9658. Min Range: -2.9658
Max Act: 2.7593. Min Act: -0.1700
Data Index: 488897 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19