Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 164 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1162. Min Range: -4.1162
Max Act: 4.1162. Min Act: -0.1700
Data Index: 1585639 (Python Code)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1162. Min Range: -4.1162
Max Act: 3.8348. Min Act: -0.1700
Data Index: 1646965 (Python Code)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1162. Min Range: -4.1162
Max Act: 3.7722. Min Act: -0.1700
Data Index: 1582751 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1162. Min Range: -4.1162
Max Act: 3.7097. Min Act: -0.1700
Data Index: 1539022 (Python Code)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1162. Min Range: -4.1162
Max Act: 3.7097. Min Act: -0.1700
Data Index: 1389546 (Python Code)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1162. Min Range: -4.1162
Max Act: 3.7097. Min Act: -0.1700
Data Index: 1585254 (Python Code)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1162. Min Range: -4.1162
Max Act: 3.6784. Min Act: -0.1700
Data Index: 1654760 (Python Code)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1162. Min Range: -4.1162
Max Act: 3.6471. Min Act: -0.1700
Data Index: 1432221 (Python Code)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1162. Min Range: -4.1162
Max Act: 3.6784. Min Act: -0.1700
Data Index: 1580152 (Python Code)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1162. Min Range: -4.1162
Max Act: 3.6471. Min Act: -0.1700
Data Index: 1637447 (Python Code)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1162. Min Range: -4.1162
Max Act: 3.6784. Min Act: -0.1700
Data Index: 1589567 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1162. Min Range: -4.1162
Max Act: 3.7097. Min Act: -0.1700
Data Index: 1389852 (Python Code)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1162. Min Range: -4.1162
Max Act: 3.7097. Min Act: -0.1700
Data Index: 1392028 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1162. Min Range: -4.1162
Max Act: 3.6784. Min Act: -0.1700
Data Index: 1396282 (Python Code)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1162. Min Range: -4.1162
Max Act: 3.6158. Min Act: -0.1700
Data Index: 1570712 (Python Code)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1162. Min Range: -4.1162
Max Act: 3.6471. Min Act: -0.1700
Data Index: 1545471 (Python Code)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1162. Min Range: -4.1162
Max Act: 3.6158. Min Act: -0.1700
Data Index: 1573420 (Python Code)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1162. Min Range: -4.1162
Max Act: 3.6784. Min Act: -0.1700
Data Index: 1433158 (Python Code)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1162. Min Range: -4.1162
Max Act: 3.6471. Min Act: -0.1700
Data Index: 1552377 (Python Code)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1162. Min Range: -4.1162
Max Act: 3.6158. Min Act: -0.1700
Data Index: 1548336 (Python Code)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19