Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 28 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.7712. Min Range: -3.7712
Max Act: 3.7712. Min Act: -0.1700
Data Index: 1448623 (Python Code)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7712. Min Range: -3.7712
Max Act: 3.7242. Min Act: -0.1700
Data Index: 1585675 (Python Code)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7712. Min Range: -3.7712
Max Act: 3.7399. Min Act: -0.1700
Data Index: 1623486 (Python Code)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7712. Min Range: -3.7712
Max Act: 3.6616. Min Act: -0.1700
Data Index: 1452441 (Python Code)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7712. Min Range: -3.7712
Max Act: 3.5834. Min Act: -0.1700
Data Index: 1395013 (Python Code)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7712. Min Range: -3.7712
Max Act: 3.5364. Min Act: -0.1700
Data Index: 1455307 (Python Code)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7712. Min Range: -3.7712
Max Act: 3.5834. Min Act: -0.1699
Data Index: 1583912 (Python Code)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7712. Min Range: -3.7712
Max Act: 3.4894. Min Act: -0.1700
Data Index: 1494381 (Python Code)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7712. Min Range: -3.7712
Max Act: 3.5207. Min Act: -0.1700
Data Index: 1536060 (Python Code)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7712. Min Range: -3.7712
Max Act: 3.4580. Min Act: -0.1700
Data Index: 1620749 (Python Code)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7712. Min Range: -3.7712
Max Act: 3.4580. Min Act: -0.1700
Data Index: 1587075 (Python Code)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7712. Min Range: -3.7712
Max Act: 3.4580. Min Act: -0.1700
Data Index: 1437804 (Python Code)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7712. Min Range: -3.7712
Max Act: 3.4267. Min Act: -0.1700
Data Index: 1427692 (Python Code)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7712. Min Range: -3.7712
Max Act: 3.4267. Min Act: -0.1700
Data Index: 1594037 (Python Code)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7712. Min Range: -3.7712
Max Act: 3.4424. Min Act: -0.1700
Data Index: 1556028 (Python Code)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7712. Min Range: -3.7712
Max Act: 3.4737. Min Act: -0.1700
Data Index: 1422183 (Python Code)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7712. Min Range: -3.7712
Max Act: 3.4110. Min Act: -0.1700
Data Index: 1357272 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7712. Min Range: -3.7712
Max Act: 3.3953. Min Act: -0.1700
Data Index: 1555318 (Python Code)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7712. Min Range: -3.7712
Max Act: 3.4424. Min Act: -0.1700
Data Index: 1588341 (Python Code)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7712. Min Range: -3.7712
Max Act: 3.4424. Min Act: -0.1700
Data Index: 1649627 (Python Code)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19