Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1993 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7190. Min Range: -2.7190
Max Act: 2.7190. Min Act: -0.1700
Data Index: 124573 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7190. Min Range: -2.7190
Max Act: 2.5423. Min Act: -0.1700
Data Index: 695645 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7190. Min Range: -2.7190
Max Act: 2.5423. Min Act: -0.1700
Data Index: 1640872 (Python Code)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7190. Min Range: -2.7190
Max Act: 2.5262. Min Act: -0.1700
Data Index: 598606 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7190. Min Range: -2.7190
Max Act: 2.5100. Min Act: -0.1700
Data Index: 680572 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7190. Min Range: -2.7190
Max Act: 2.5100. Min Act: -0.1700
Data Index: 1450569 (Python Code)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7190. Min Range: -2.7190
Max Act: 2.5100. Min Act: -0.1700
Data Index: 105858 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7190. Min Range: -2.7190
Max Act: 2.4938. Min Act: -0.1700
Data Index: 915266 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7190. Min Range: -2.7190
Max Act: 2.4938. Min Act: -0.1700
Data Index: 985943 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7190. Min Range: -2.7190
Max Act: 2.4776. Min Act: -0.1700
Data Index: 15630 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7190. Min Range: -2.7190
Max Act: 2.4776. Min Act: -0.1700
Data Index: 117806 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7190. Min Range: -2.7190
Max Act: 2.4776. Min Act: -0.1700
Data Index: 374337 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7190. Min Range: -2.7190
Max Act: 2.4776. Min Act: -0.1700
Data Index: 746572 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7190. Min Range: -2.7190
Max Act: 2.4614. Min Act: -0.1700
Data Index: 987400 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7190. Min Range: -2.7190
Max Act: 2.4614. Min Act: -0.1700
Data Index: 1637874 (Python Code)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7190. Min Range: -2.7190
Max Act: 2.4288. Min Act: -0.1700
Data Index: 931686 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7190. Min Range: -2.7190
Max Act: 2.4451. Min Act: -0.1700
Data Index: 91892 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7190. Min Range: -2.7190
Max Act: 2.4451. Min Act: -0.1700
Data Index: 173943 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7190. Min Range: -2.7190
Max Act: 2.4451. Min Act: -0.1700
Data Index: 1344970 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7190. Min Range: -2.7190
Max Act: 2.4451. Min Act: -0.1700
Data Index: 1362359 (Python Code)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19