Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2005 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.8730. Min Range: -4.8730
Max Act: 4.8730. Min Act: -0.1700
Data Index: 1607143 (Python Code)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8730. Min Range: -4.8730
Max Act: 4.8105. Min Act: -0.1700
Data Index: 1432721 (Python Code)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8730. Min Range: -4.8730
Max Act: 4.7792. Min Act: -0.1700
Data Index: 1438912 (Python Code)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8730. Min Range: -4.8730
Max Act: 4.8105. Min Act: -0.1700
Data Index: 1425662 (Python Code)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8730. Min Range: -4.8730
Max Act: 4.8417. Min Act: -0.1700
Data Index: 1378192 (Python Code)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8730. Min Range: -4.8730
Max Act: 4.7792. Min Act: -0.1700
Data Index: 1463743 (Python Code)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8730. Min Range: -4.8730
Max Act: 4.7480. Min Act: -0.1700
Data Index: 1598997 (Python Code)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8730. Min Range: -4.8730
Max Act: 4.8417. Min Act: -0.1700
Data Index: 1370367 (Python Code)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8730. Min Range: -4.8730
Max Act: 4.8105. Min Act: -0.1700
Data Index: 1546519 (Python Code)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8730. Min Range: -4.8730
Max Act: 4.7480. Min Act: -0.1700
Data Index: 1458057 (Python Code)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8730. Min Range: -4.8730
Max Act: 4.7792. Min Act: -0.1700
Data Index: 1468235 (Python Code)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8730. Min Range: -4.8730
Max Act: 4.7480. Min Act: -0.1700
Data Index: 1618520 (Python Code)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8730. Min Range: -4.8730
Max Act: 4.7480. Min Act: -0.1700
Data Index: 1411103 (Python Code)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8730. Min Range: -4.8730
Max Act: 4.7792. Min Act: -0.1700
Data Index: 1611102 (Python Code)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8730. Min Range: -4.8730
Max Act: 4.7480. Min Act: -0.1700
Data Index: 1591155 (Python Code)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8730. Min Range: -4.8730
Max Act: 4.7480. Min Act: -0.1700
Data Index: 1588410 (Python Code)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8730. Min Range: -4.8730
Max Act: 4.7480. Min Act: -0.1700
Data Index: 1504574 (Python Code)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8730. Min Range: -4.8730
Max Act: 4.7167. Min Act: -0.1700
Data Index: 1452465 (Python Code)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8730. Min Range: -4.8730
Max Act: 4.7167. Min Act: -0.1700
Data Index: 1496730 (Python Code)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8730. Min Range: -4.8730
Max Act: 4.7792. Min Act: -0.1700
Data Index: 1493967 (Python Code)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19