Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1470 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.2483. Min Range: -2.2483
Max Act: 2.2483. Min Act: -0.1700
Data Index: 1228584 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2483. Min Range: -2.2483
Max Act: 2.1654. Min Act: -0.1700
Data Index: 1596633 (Python Code)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2483. Min Range: -2.2483
Max Act: 2.1488. Min Act: -0.1700
Data Index: 703454 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2483. Min Range: -2.2483
Max Act: 2.1321. Min Act: -0.1700
Data Index: 1511177 (Python Code)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2483. Min Range: -2.2483
Max Act: 2.1154. Min Act: -0.1700
Data Index: 1602293 (Python Code)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2483. Min Range: -2.2483
Max Act: 2.1321. Min Act: -0.1700
Data Index: 1429696 (Python Code)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2483. Min Range: -2.2483
Max Act: 2.1321. Min Act: -0.1700
Data Index: 1543543 (Python Code)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2483. Min Range: -2.2483
Max Act: 2.1154. Min Act: -0.1700
Data Index: 1481137 (Python Code)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2483. Min Range: -2.2483
Max Act: 2.1321. Min Act: -0.1700
Data Index: 310577 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2483. Min Range: -2.2483
Max Act: 2.0987. Min Act: -0.1700
Data Index: 1215766 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2483. Min Range: -2.2483
Max Act: 2.0987. Min Act: -0.1700
Data Index: 574920 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2483. Min Range: -2.2483
Max Act: 2.0820. Min Act: -0.1700
Data Index: 313942 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2483. Min Range: -2.2483
Max Act: 2.0820. Min Act: -0.1700
Data Index: 1438149 (Python Code)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2483. Min Range: -2.2483
Max Act: 2.0987. Min Act: -0.1700
Data Index: 1647597 (Python Code)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2483. Min Range: -2.2483
Max Act: 2.0820. Min Act: -0.1700
Data Index: 1641014 (Python Code)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2483. Min Range: -2.2483
Max Act: 2.0820. Min Act: -0.1700
Data Index: 1626644 (Python Code)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2483. Min Range: -2.2483
Max Act: 2.0652. Min Act: -0.1700
Data Index: 1626117 (Python Code)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2483. Min Range: -2.2483
Max Act: 2.0820. Min Act: -0.1700
Data Index: 674678 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2483. Min Range: -2.2483
Max Act: 2.0820. Min Act: -0.1700
Data Index: 700543 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2483. Min Range: -2.2483
Max Act: 2.0820. Min Act: -0.1700
Data Index: 68241 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19