Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 878 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3297. Min Range: -4.3297
Max Act: 4.3297. Min Act: -0.1700
Data Index: 1550948 (Python Code)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3297. Min Range: -4.3297
Max Act: 4.3297. Min Act: -0.1700
Data Index: 1555195 (Python Code)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3297. Min Range: -4.3297
Max Act: 4.2672. Min Act: -0.1700
Data Index: 1472858 (Python Code)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3297. Min Range: -4.3297
Max Act: 4.2047. Min Act: -0.1700
Data Index: 1467890 (Python Code)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3297. Min Range: -4.3297
Max Act: 4.2359. Min Act: -0.1700
Data Index: 1415614 (Python Code)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3297. Min Range: -4.3297
Max Act: 4.1734. Min Act: -0.1700
Data Index: 1373666 (Python Code)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3297. Min Range: -4.3297
Max Act: 4.2047. Min Act: -0.1700
Data Index: 1609831 (Python Code)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3297. Min Range: -4.3297
Max Act: 4.0796. Min Act: -0.1700
Data Index: 325880 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3297. Min Range: -4.3297
Max Act: 4.0796. Min Act: -0.1700
Data Index: 1566989 (Python Code)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3297. Min Range: -4.3297
Max Act: 4.0484. Min Act: -0.1700
Data Index: 1581415 (Python Code)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3297. Min Range: -4.3297
Max Act: 4.0796. Min Act: -0.1700
Data Index: 1366897 (Python Code)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3297. Min Range: -4.3297
Max Act: 4.0484. Min Act: -0.1700
Data Index: 1402605 (Python Code)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3297. Min Range: -4.3297
Max Act: 4.0796. Min Act: -0.1700
Data Index: 1429074 (Python Code)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3297. Min Range: -4.3297
Max Act: 4.0796. Min Act: -0.1700
Data Index: 1400356 (Python Code)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3297. Min Range: -4.3297
Max Act: 4.0171. Min Act: -0.1700
Data Index: 543712 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3297. Min Range: -4.3297
Max Act: 4.0484. Min Act: -0.1700
Data Index: 1113569 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3297. Min Range: -4.3297
Max Act: 4.0796. Min Act: -0.1700
Data Index: 694459 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3297. Min Range: -4.3297
Max Act: 4.0484. Min Act: -0.1700
Data Index: 1382821 (Python Code)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3297. Min Range: -4.3297
Max Act: 4.0171. Min Act: -0.1700
Data Index: 1504265 (Python Code)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3297. Min Range: -4.3297
Max Act: 4.0171. Min Act: -0.1700
Data Index: 1581559 (Python Code)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19