Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1998 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.4379. Min Range: -4.4379
Max Act: 4.4379. Min Act: -0.1700
Data Index: 907762 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4379. Min Range: -4.4379
Max Act: 4.2504. Min Act: -0.1700
Data Index: 285100 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4379. Min Range: -4.4379
Max Act: 4.1410. Min Act: -0.1700
Data Index: 129953 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4379. Min Range: -4.4379
Max Act: 4.1253. Min Act: -0.1700
Data Index: 562421 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4379. Min Range: -4.4379
Max Act: 4.0941. Min Act: -0.1700
Data Index: 761561 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4379. Min Range: -4.4379
Max Act: 4.0784. Min Act: -0.1700
Data Index: 168502 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4379. Min Range: -4.4379
Max Act: 4.0628. Min Act: -0.1700
Data Index: 54413 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4379. Min Range: -4.4379
Max Act: 4.0472. Min Act: -0.1700
Data Index: 897697 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4379. Min Range: -4.4379
Max Act: 4.0159. Min Act: -0.1700
Data Index: 1072340 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4379. Min Range: -4.4379
Max Act: 3.9534. Min Act: -0.1700
Data Index: 714611 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4379. Min Range: -4.4379
Max Act: 3.9534. Min Act: -0.1700
Data Index: 713315 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4379. Min Range: -4.4379
Max Act: 3.9846. Min Act: -0.1700
Data Index: 1020990 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4379. Min Range: -4.4379
Max Act: 3.9377. Min Act: -0.1700
Data Index: 132156 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4379. Min Range: -4.4379
Max Act: 3.9377. Min Act: -0.1700
Data Index: 1193130 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4379. Min Range: -4.4379
Max Act: 3.9534. Min Act: -0.1700
Data Index: 773719 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4379. Min Range: -4.4379
Max Act: 3.9377. Min Act: -0.1700
Data Index: 893655 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4379. Min Range: -4.4379
Max Act: 3.9221. Min Act: -0.1700
Data Index: 320116 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4379. Min Range: -4.4379
Max Act: 3.8908. Min Act: -0.1700
Data Index: 1137911 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4379. Min Range: -4.4379
Max Act: 3.9065. Min Act: -0.1700
Data Index: 519932 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4379. Min Range: -4.4379
Max Act: 3.8908. Min Act: -0.1700
Data Index: 918062 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19