Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 402 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.2218. Min Range: -4.2218
Max Act: 4.2218. Min Act: -0.1700
Data Index: 1103447 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2218. Min Range: -4.2218
Max Act: 4.1593. Min Act: -0.1700
Data Index: 1556132 (Python Code)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2218. Min Range: -4.2218
Max Act: 4.1437. Min Act: -0.1700
Data Index: 49619 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2218. Min Range: -4.2218
Max Act: 4.0968. Min Act: -0.1700
Data Index: 1010213 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2218. Min Range: -4.2218
Max Act: 4.0968. Min Act: -0.1700
Data Index: 693398 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2218. Min Range: -4.2218
Max Act: 4.0968. Min Act: -0.1700
Data Index: 1124841 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2218. Min Range: -4.2218
Max Act: 4.0655. Min Act: -0.1700
Data Index: 220744 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2218. Min Range: -4.2218
Max Act: 4.0812. Min Act: -0.1700
Data Index: 942289 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2218. Min Range: -4.2218
Max Act: 4.0655. Min Act: -0.1700
Data Index: 60031 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2218. Min Range: -4.2218
Max Act: 4.0812. Min Act: -0.1700
Data Index: 1337149 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2218. Min Range: -4.2218
Max Act: 4.0186. Min Act: -0.1700
Data Index: 210377 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2218. Min Range: -4.2218
Max Act: 4.0499. Min Act: -0.1700
Data Index: 342079 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2218. Min Range: -4.2218
Max Act: 4.0343. Min Act: -0.1700
Data Index: 1485094 (Python Code)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2218. Min Range: -4.2218
Max Act: 4.0343. Min Act: -0.1700
Data Index: 1100306 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2218. Min Range: -4.2218
Max Act: 4.0186. Min Act: -0.1700
Data Index: 601019 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2218. Min Range: -4.2218
Max Act: 4.0030. Min Act: -0.1700
Data Index: 1447813 (Python Code)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2218. Min Range: -4.2218
Max Act: 4.0030. Min Act: -0.1700
Data Index: 1435633 (Python Code)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2218. Min Range: -4.2218
Max Act: 4.0030. Min Act: -0.1700
Data Index: 552187 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2218. Min Range: -4.2218
Max Act: 3.9874. Min Act: -0.1700
Data Index: 1288053 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2218. Min Range: -4.2218
Max Act: 4.0030. Min Act: -0.1700
Data Index: 767138 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19