Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1995 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.7550. Min Range: -4.7550
Max Act: 4.7550. Min Act: -0.1700
Data Index: 773052 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7550. Min Range: -4.7550
Max Act: 4.7237. Min Act: -0.1700
Data Index: 503080 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7550. Min Range: -4.7550
Max Act: 4.6612. Min Act: -0.1700
Data Index: 80854 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7550. Min Range: -4.7550
Max Act: 4.6300. Min Act: -0.1700
Data Index: 220434 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7550. Min Range: -4.7550
Max Act: 4.6300. Min Act: -0.1700
Data Index: 561344 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7550. Min Range: -4.7550
Max Act: 4.5987. Min Act: -0.1700
Data Index: 994506 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7550. Min Range: -4.7550
Max Act: 4.5987. Min Act: -0.1700
Data Index: 767684 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7550. Min Range: -4.7550
Max Act: 4.5987. Min Act: -0.1700
Data Index: 1335424 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7550. Min Range: -4.7550
Max Act: 4.5987. Min Act: -0.1700
Data Index: 10968 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7550. Min Range: -4.7550
Max Act: 4.5362. Min Act: -0.1700
Data Index: 240916 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7550. Min Range: -4.7550
Max Act: 4.5675. Min Act: -0.1700
Data Index: 338404 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7550. Min Range: -4.7550
Max Act: 4.5362. Min Act: -0.1700
Data Index: 214967 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7550. Min Range: -4.7550
Max Act: 4.5675. Min Act: -0.1700
Data Index: 858238 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7550. Min Range: -4.7550
Max Act: 4.5362. Min Act: -0.1700
Data Index: 250184 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7550. Min Range: -4.7550
Max Act: 4.5362. Min Act: -0.1700
Data Index: 760943 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7550. Min Range: -4.7550
Max Act: 4.5675. Min Act: -0.1700
Data Index: 316247 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7550. Min Range: -4.7550
Max Act: 4.5050. Min Act: -0.1700
Data Index: 100435 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7550. Min Range: -4.7550
Max Act: 4.5362. Min Act: -0.1700
Data Index: 532960 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7550. Min Range: -4.7550
Max Act: 4.5050. Min Act: -0.1700
Data Index: 463462 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7550. Min Range: -4.7550
Max Act: 4.4737. Min Act: -0.1700
Data Index: 8728 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19