Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2004 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 5.0408. Min Range: -5.0408
Max Act: 5.0408. Min Act: -0.1700
Data Index: 1206106 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0408. Min Range: -5.0408
Max Act: 4.9471. Min Act: -0.1700
Data Index: 605381 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0408. Min Range: -5.0408
Max Act: 4.9783. Min Act: -0.1700
Data Index: 433016 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0408. Min Range: -5.0408
Max Act: 4.9471. Min Act: -0.1700
Data Index: 957015 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0408. Min Range: -5.0408
Max Act: 4.9783. Min Act: -0.1700
Data Index: 455880 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0408. Min Range: -5.0408
Max Act: 4.9471. Min Act: -0.1700
Data Index: 1193614 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0408. Min Range: -5.0408
Max Act: 4.9471. Min Act: -0.1700
Data Index: 1261754 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0408. Min Range: -5.0408
Max Act: 4.8846. Min Act: -0.1700
Data Index: 572029 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0408. Min Range: -5.0408
Max Act: 4.8846. Min Act: -0.1700
Data Index: 4069 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0408. Min Range: -5.0408
Max Act: 4.9158. Min Act: -0.1700
Data Index: 238349 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0408. Min Range: -5.0408
Max Act: 4.9158. Min Act: -0.1700
Data Index: 1330168 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0408. Min Range: -5.0408
Max Act: 4.9158. Min Act: -0.1700
Data Index: 854656 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0408. Min Range: -5.0408
Max Act: 4.9158. Min Act: -0.1700
Data Index: 794219 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0408. Min Range: -5.0408
Max Act: 4.8846. Min Act: -0.1700
Data Index: 1112148 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0408. Min Range: -5.0408
Max Act: 4.8846. Min Act: -0.1700
Data Index: 1340228 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0408. Min Range: -5.0408
Max Act: 4.8533. Min Act: -0.1700
Data Index: 312774 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0408. Min Range: -5.0408
Max Act: 4.8533. Min Act: -0.1700
Data Index: 1026202 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0408. Min Range: -5.0408
Max Act: 4.8533. Min Act: -0.1700
Data Index: 900142 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0408. Min Range: -5.0408
Max Act: 4.8533. Min Act: -0.1700
Data Index: 11286 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0408. Min Range: -5.0408
Max Act: 4.8221. Min Act: -0.1700
Data Index: 56117 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19