Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 23 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.7448. Min Range: -6.7448
Max Act: 6.7448. Min Act: -0.1700
Data Index: 1535582 (Python Code)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7448. Min Range: -6.7448
Max Act: 6.7448. Min Act: -0.1700
Data Index: 960061 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7448. Min Range: -6.7448
Max Act: 6.6198. Min Act: -0.1700
Data Index: 1541876 (Python Code)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7448. Min Range: -6.7448
Max Act: 6.6823. Min Act: -0.1700
Data Index: 1389290 (Python Code)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7448. Min Range: -6.7448
Max Act: 6.5573. Min Act: -0.1700
Data Index: 1490378 (Python Code)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7448. Min Range: -6.7448
Max Act: 6.4635. Min Act: -0.1700
Data Index: 1081549 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7448. Min Range: -6.7448
Max Act: 6.5573. Min Act: -0.1700
Data Index: 1639055 (Python Code)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7448. Min Range: -6.7448
Max Act: 6.4010. Min Act: -0.1700
Data Index: 1498644 (Python Code)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7448. Min Range: -6.7448
Max Act: 6.3698. Min Act: -0.1700
Data Index: 1599721 (Python Code)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7448. Min Range: -6.7448
Max Act: 6.2760. Min Act: -0.1700
Data Index: 1467574 (Python Code)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7448. Min Range: -6.7448
Max Act: 6.2448. Min Act: -0.1700
Data Index: 1459109 (Python Code)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7448. Min Range: -6.7448
Max Act: 6.2760. Min Act: -0.1700
Data Index: 1499295 (Python Code)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7448. Min Range: -6.7448
Max Act: 6.3073. Min Act: -0.1700
Data Index: 1587423 (Python Code)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7448. Min Range: -6.7448
Max Act: 6.3073. Min Act: -0.1700
Data Index: 1374201 (Python Code)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7448. Min Range: -6.7448
Max Act: 6.3073. Min Act: -0.1700
Data Index: 1414382 (Python Code)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7448. Min Range: -6.7448
Max Act: 6.2448. Min Act: -0.1699
Data Index: 1096415 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7448. Min Range: -6.7448
Max Act: 6.2760. Min Act: -0.1700
Data Index: 1611432 (Python Code)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7448. Min Range: -6.7448
Max Act: 6.2448. Min Act: -0.1700
Data Index: 1524389 (Python Code)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7448. Min Range: -6.7448
Max Act: 6.2760. Min Act: -0.1700
Data Index: 1550782 (Python Code)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7448. Min Range: -6.7448
Max Act: 6.1510. Min Act: -0.1700
Data Index: 252089 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19