Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 140 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.5507. Min Range: -4.5507
Max Act: 4.5507. Min Act: -0.1700
Data Index: 1358553 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5507. Min Range: -4.5507
Max Act: 4.4882. Min Act: -0.1700
Data Index: 15926 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5507. Min Range: -4.5507
Max Act: 4.3944. Min Act: -0.1700
Data Index: 6727 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5507. Min Range: -4.5507
Max Act: 4.4257. Min Act: -0.1700
Data Index: 79381 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5507. Min Range: -4.5507
Max Act: 4.3944. Min Act: -0.1700
Data Index: 115572 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5507. Min Range: -4.5507
Max Act: 4.3944. Min Act: -0.1700
Data Index: 1292785 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5507. Min Range: -4.5507
Max Act: 4.3319. Min Act: -0.1700
Data Index: 544216 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5507. Min Range: -4.5507
Max Act: 4.3632. Min Act: -0.1700
Data Index: 856536 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5507. Min Range: -4.5507
Max Act: 4.2694. Min Act: -0.1700
Data Index: 117499 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5507. Min Range: -4.5507
Max Act: 4.3319. Min Act: -0.1700
Data Index: 352630 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5507. Min Range: -4.5507
Max Act: 4.3319. Min Act: -0.1700
Data Index: 736679 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5507. Min Range: -4.5507
Max Act: 4.3007. Min Act: -0.1700
Data Index: 928602 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5507. Min Range: -4.5507
Max Act: 4.3632. Min Act: -0.1700
Data Index: 636767 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5507. Min Range: -4.5507
Max Act: 4.3007. Min Act: -0.1700
Data Index: 435917 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5507. Min Range: -4.5507
Max Act: 4.2382. Min Act: -0.1700
Data Index: 112223 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5507. Min Range: -4.5507
Max Act: 4.2382. Min Act: -0.1700
Data Index: 295399 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5507. Min Range: -4.5507
Max Act: 4.2694. Min Act: -0.1700
Data Index: 308656 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5507. Min Range: -4.5507
Max Act: 4.2382. Min Act: -0.1700
Data Index: 64628 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5507. Min Range: -4.5507
Max Act: 4.2382. Min Act: -0.1700
Data Index: 1356868 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5507. Min Range: -4.5507
Max Act: 4.2382. Min Act: -0.1700
Data Index: 522011 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19