Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 803 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.7961. Min Range: -4.7961
Max Act: 4.7961. Min Act: -0.1700
Data Index: 199560 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7961. Min Range: -4.7961
Max Act: 4.7649. Min Act: -0.1700
Data Index: 488692 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7961. Min Range: -4.7961
Max Act: 4.7336. Min Act: -0.1700
Data Index: 399250 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7961. Min Range: -4.7961
Max Act: 4.7649. Min Act: -0.1700
Data Index: 1267602 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7961. Min Range: -4.7961
Max Act: 4.6711. Min Act: -0.1700
Data Index: 930087 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7961. Min Range: -4.7961
Max Act: 4.6711. Min Act: -0.1700
Data Index: 672812 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7961. Min Range: -4.7961
Max Act: 4.5774. Min Act: -0.1700
Data Index: 453817 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7961. Min Range: -4.7961
Max Act: 4.6399. Min Act: -0.1699
Data Index: 1246097 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7961. Min Range: -4.7961
Max Act: 4.6086. Min Act: -0.1700
Data Index: 845302 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7961. Min Range: -4.7961
Max Act: 4.6711. Min Act: -0.1700
Data Index: 624093 (C4 (Web Text))
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7961. Min Range: -4.7961
Max Act: 4.5461. Min Act: -0.1700
Data Index: 248336 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7961. Min Range: -4.7961
Max Act: 4.5461. Min Act: -0.1700
Data Index: 774058 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7961. Min Range: -4.7961
Max Act: 4.4524. Min Act: -0.1700
Data Index: 313304 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7961. Min Range: -4.7961
Max Act: 4.5461. Min Act: -0.1700
Data Index: 476505 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7961. Min Range: -4.7961
Max Act: 4.4524. Min Act: -0.1700
Data Index: 893520 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7961. Min Range: -4.7961
Max Act: 4.5461. Min Act: -0.1700
Data Index: 504313 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7961. Min Range: -4.7961
Max Act: 4.4836. Min Act: -0.1700
Data Index: 940753 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7961. Min Range: -4.7961
Max Act: 4.4524. Min Act: -0.1700
Data Index: 461948 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7961. Min Range: -4.7961
Max Act: 4.4836. Min Act: -0.1700
Data Index: 67624 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7961. Min Range: -4.7961
Max Act: 4.4524. Min Act: -0.1700
Data Index: 103867 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19