Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1705 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7426. Min Range: -2.7426
Max Act: 2.7426. Min Act: -0.1700
Data Index: 1606535 (Python Code)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7426. Min Range: -2.7426
Max Act: 2.5661. Min Act: -0.1700
Data Index: 1614927 (Python Code)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7426. Min Range: -2.7426
Max Act: 2.5500. Min Act: -0.1700
Data Index: 1651890 (Python Code)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7426. Min Range: -2.7426
Max Act: 2.5500. Min Act: -0.1700
Data Index: 1636134 (Python Code)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7426. Min Range: -2.7426
Max Act: 2.5177. Min Act: -0.1700
Data Index: 1000549 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7426. Min Range: -2.7426
Max Act: 2.5338. Min Act: -0.1700
Data Index: 1458710 (Python Code)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7426. Min Range: -2.7426
Max Act: 2.5177. Min Act: -0.1700
Data Index: 1588111 (Python Code)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7426. Min Range: -2.7426
Max Act: 2.5177. Min Act: -0.1700
Data Index: 1583090 (Python Code)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7426. Min Range: -2.7426
Max Act: 2.5015. Min Act: -0.1700
Data Index: 1628556 (Python Code)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7426. Min Range: -2.7426
Max Act: 2.5015. Min Act: -0.1700
Data Index: 1625350 (Python Code)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7426. Min Range: -2.7426
Max Act: 2.4690. Min Act: -0.1700
Data Index: 1389712 (Python Code)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7426. Min Range: -2.7426
Max Act: 2.4690. Min Act: -0.1700
Data Index: 1622102 (Python Code)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7426. Min Range: -2.7426
Max Act: 2.4690. Min Act: -0.1700
Data Index: 1448552 (Python Code)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7426. Min Range: -2.7426
Max Act: 2.4690. Min Act: -0.1699
Data Index: 1603563 (Python Code)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7426. Min Range: -2.7426
Max Act: 2.4690. Min Act: -0.1700
Data Index: 1644552 (Python Code)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7426. Min Range: -2.7426
Max Act: 2.4528. Min Act: -0.1700
Data Index: 1362654 (Python Code)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7426. Min Range: -2.7426
Max Act: 2.4528. Min Act: -0.1700
Data Index: 1395363 (Python Code)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7426. Min Range: -2.7426
Max Act: 2.4528. Min Act: -0.1700
Data Index: 1468801 (Python Code)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7426. Min Range: -2.7426
Max Act: 2.4528. Min Act: -0.1700
Data Index: 1438410 (Python Code)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7426. Min Range: -2.7426
Max Act: 2.4528. Min Act: -0.1700
Data Index: 1607471 (Python Code)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19