Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 63 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.3279. Min Range: -2.3279
Max Act: 2.3279. Min Act: -0.1700
Data Index: 1627988 (Python Code)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3279. Min Range: -2.3279
Max Act: 2.2621. Min Act: -0.1613
Data Index: 1594282 (Python Code)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3279. Min Range: -2.3279
Max Act: 2.2456. Min Act: -0.1700
Data Index: 1586691 (Python Code)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3279. Min Range: -2.3279
Max Act: 2.1127. Min Act: -0.1700
Data Index: 1360792 (Python Code)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3279. Min Range: -2.3279
Max Act: 2.0288. Min Act: -0.1700
Data Index: 1411055 (Python Code)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3279. Min Range: -2.3279
Max Act: 2.0288. Min Act: -0.1700
Data Index: 1407262 (Python Code)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3279. Min Range: -2.3279
Max Act: 2.0456. Min Act: -0.1700
Data Index: 1391712 (Python Code)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3279. Min Range: -2.3279
Max Act: 2.0288. Min Act: -0.1699
Data Index: 1443476 (Python Code)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3279. Min Range: -2.3279
Max Act: 2.0119. Min Act: -0.1700
Data Index: 1646819 (Python Code)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3279. Min Range: -2.3279
Max Act: 1.9951. Min Act: -0.1700
Data Index: 1580619 (Python Code)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3279. Min Range: -2.3279
Max Act: 1.9951. Min Act: -0.1700
Data Index: 1657003 (Python Code)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3279. Min Range: -2.3279
Max Act: 1.9951. Min Act: -0.1700
Data Index: 1654388 (Python Code)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3279. Min Range: -2.3279
Max Act: 2.0119. Min Act: -0.1700
Data Index: 1533332 (Python Code)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3279. Min Range: -2.3279
Max Act: 2.0119. Min Act: -0.1697
Data Index: 1453197 (Python Code)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3279. Min Range: -2.3279
Max Act: 2.0119. Min Act: -0.1700
Data Index: 1600979 (Python Code)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3279. Min Range: -2.3279
Max Act: 1.9782. Min Act: -0.1700
Data Index: 1640947 (Python Code)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3279. Min Range: -2.3279
Max Act: 1.9951. Min Act: -0.1649
Data Index: 1601532 (Python Code)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3279. Min Range: -2.3279
Max Act: 1.9612. Min Act: -0.1700
Data Index: 1647608 (Python Code)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3279. Min Range: -2.3279
Max Act: 1.9612. Min Act: -0.1700
Data Index: 1443774 (Python Code)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3279. Min Range: -2.3279
Max Act: 1.9782. Min Act: -0.1699
Data Index: 1568790 (Python Code)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19