Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 133 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4946. Min Range: -2.4946
Max Act: 2.4946. Min Act: -0.1700
Data Index: 1651971 (Python Code)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4946. Min Range: -2.4946
Max Act: 2.4784. Min Act: -0.1700
Data Index: 1459230 (Python Code)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4946. Min Range: -2.4946
Max Act: 2.3971. Min Act: -0.1700
Data Index: 1529162 (Python Code)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4946. Min Range: -2.4946
Max Act: 2.3644. Min Act: -0.1700
Data Index: 1543145 (Python Code)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4946. Min Range: -2.4946
Max Act: 2.3480. Min Act: -0.1700
Data Index: 1489817 (Python Code)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4946. Min Range: -2.4946
Max Act: 2.3317. Min Act: -0.1700
Data Index: 1441614 (Python Code)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4946. Min Range: -2.4946
Max Act: 2.3317. Min Act: -0.1700
Data Index: 1461167 (Python Code)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4946. Min Range: -2.4946
Max Act: 2.3317. Min Act: -0.1700
Data Index: 1512176 (Python Code)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4946. Min Range: -2.4946
Max Act: 2.3317. Min Act: -0.1700
Data Index: 1374707 (Python Code)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4946. Min Range: -2.4946
Max Act: 2.3317. Min Act: -0.1700
Data Index: 1549038 (Python Code)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4946. Min Range: -2.4946
Max Act: 2.2988. Min Act: -0.1700
Data Index: 1597106 (Python Code)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4946. Min Range: -2.4946
Max Act: 2.3152. Min Act: -0.1700
Data Index: 1460573 (Python Code)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4946. Min Range: -2.4946
Max Act: 2.3152. Min Act: -0.1700
Data Index: 1426381 (Python Code)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4946. Min Range: -2.4946
Max Act: 2.2988. Min Act: -0.1700
Data Index: 1563265 (Python Code)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4946. Min Range: -2.4946
Max Act: 2.2824. Min Act: -0.1700
Data Index: 1642434 (Python Code)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4946. Min Range: -2.4946
Max Act: 2.2659. Min Act: -0.1700
Data Index: 1482690 (Python Code)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4946. Min Range: -2.4946
Max Act: 2.2659. Min Act: -0.1700
Data Index: 1423756 (Python Code)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4946. Min Range: -2.4946
Max Act: 2.2659. Min Act: -0.1700
Data Index: 1392326 (Python Code)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4946. Min Range: -2.4946
Max Act: 2.2659. Min Act: -0.1700
Data Index: 1528618 (Python Code)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4946. Min Range: -2.4946
Max Act: 2.2659. Min Act: -0.1700
Data Index: 1607582 (Python Code)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19