Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2040 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.3613. Min Range: -2.3613
Max Act: 2.3613. Min Act: -0.1700
Data Index: 1451290 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3613. Min Range: -2.3613
Max Act: 2.2957. Min Act: -0.1700
Data Index: 1560542 (Python Code)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3613. Min Range: -2.3613
Max Act: 2.2792. Min Act: -0.1700
Data Index: 1623333 (Python Code)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3613. Min Range: -2.3613
Max Act: 2.2792. Min Act: -0.1700
Data Index: 1474558 (Python Code)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3613. Min Range: -2.3613
Max Act: 2.2463. Min Act: -0.1700
Data Index: 1494827 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3613. Min Range: -2.3613
Max Act: 2.2297. Min Act: -0.1700
Data Index: 1621754 (Python Code)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3613. Min Range: -2.3613
Max Act: 2.2297. Min Act: -0.1700
Data Index: 1380626 (Python Code)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3613. Min Range: -2.3613
Max Act: 2.2297. Min Act: -0.1700
Data Index: 1519090 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3613. Min Range: -2.3613
Max Act: 2.2297. Min Act: -0.1700
Data Index: 1604568 (Python Code)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3613. Min Range: -2.3613
Max Act: 2.2132. Min Act: -0.1700
Data Index: 1501113 (Python Code)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3613. Min Range: -2.3613
Max Act: 2.2132. Min Act: -0.1700
Data Index: 1373669 (Python Code)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3613. Min Range: -2.3613
Max Act: 2.2132. Min Act: -0.1700
Data Index: 1648532 (Python Code)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3613. Min Range: -2.3613
Max Act: 2.2132. Min Act: -0.1700
Data Index: 1472164 (Python Code)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3613. Min Range: -2.3613
Max Act: 2.2132. Min Act: -0.1700
Data Index: 1566804 (Python Code)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3613. Min Range: -2.3613
Max Act: 2.1966. Min Act: -0.1700
Data Index: 1509241 (Python Code)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3613. Min Range: -2.3613
Max Act: 2.1966. Min Act: -0.1700
Data Index: 1647214 (Python Code)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3613. Min Range: -2.3613
Max Act: 2.1966. Min Act: -0.1700
Data Index: 1629525 (Python Code)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3613. Min Range: -2.3613
Max Act: 2.1966. Min Act: -0.1700
Data Index: 1627719 (Python Code)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3613. Min Range: -2.3613
Max Act: 2.1966. Min Act: -0.1700
Data Index: 1549966 (Python Code)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3613. Min Range: -2.3613
Max Act: 2.1966. Min Act: -0.1700
Data Index: 1451022 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19