Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 871 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.1414. Min Range: -4.1414
Max Act: 4.1414. Min Act: -0.1700
Data Index: 1363609 (Python Code)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1414. Min Range: -4.1414
Max Act: 4.0789. Min Act: -0.1700
Data Index: 1487785 (Python Code)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1414. Min Range: -4.1414
Max Act: 4.0476. Min Act: -0.1700
Data Index: 1443848 (Python Code)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1414. Min Range: -4.1414
Max Act: 3.9069. Min Act: -0.1700
Data Index: 1639398 (Python Code)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1414. Min Range: -4.1414
Max Act: 3.8444. Min Act: -0.1700
Data Index: 1472643 (Python Code)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1414. Min Range: -4.1414
Max Act: 3.8600. Min Act: -0.1700
Data Index: 1537220 (Python Code)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1414. Min Range: -4.1414
Max Act: 3.8444. Min Act: -0.1700
Data Index: 1545557 (Python Code)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1414. Min Range: -4.1414
Max Act: 3.7662. Min Act: -0.1700
Data Index: 1043980 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1414. Min Range: -4.1414
Max Act: 3.7662. Min Act: -0.1700
Data Index: 1634026 (Python Code)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1414. Min Range: -4.1414
Max Act: 3.7975. Min Act: -0.1700
Data Index: 1643968 (Python Code)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1414. Min Range: -4.1414
Max Act: 3.7662. Min Act: -0.1700
Data Index: 1627880 (Python Code)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1414. Min Range: -4.1414
Max Act: 3.7349. Min Act: -0.1700
Data Index: 1435961 (Python Code)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1414. Min Range: -4.1414
Max Act: 3.7036. Min Act: -0.1700
Data Index: 969177 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1414. Min Range: -4.1414
Max Act: 3.7662. Min Act: -0.1700
Data Index: 1429450 (Python Code)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1414. Min Range: -4.1414
Max Act: 3.7505. Min Act: -0.1700
Data Index: 1406969 (Python Code)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1414. Min Range: -4.1414
Max Act: 3.7349. Min Act: -0.1700
Data Index: 1444459 (Python Code)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1414. Min Range: -4.1414
Max Act: 3.7036. Min Act: -0.1700
Data Index: 1550885 (Python Code)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1414. Min Range: -4.1414
Max Act: 3.6880. Min Act: -0.1700
Data Index: 1525127 (Python Code)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1414. Min Range: -4.1414
Max Act: 3.7349. Min Act: -0.1700
Data Index: 1618259 (Python Code)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1414. Min Range: -4.1414
Max Act: 3.6723. Min Act: -0.1700
Data Index: 1607824 (Python Code)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19