Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2001 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.3858. Min Range: -4.3858
Max Act: 4.3858. Min Act: -0.1700
Data Index: 1589877 (Python Code)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3858. Min Range: -4.3858
Max Act: 4.2608. Min Act: -0.1700
Data Index: 1383205 (Python Code)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3858. Min Range: -4.3858
Max Act: 4.2608. Min Act: -0.1700
Data Index: 1548495 (Python Code)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3858. Min Range: -4.3858
Max Act: 4.1983. Min Act: -0.1700
Data Index: 1302408 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3858. Min Range: -4.3858
Max Act: 4.2295. Min Act: -0.1699
Data Index: 1414266 (Python Code)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3858. Min Range: -4.3858
Max Act: 4.1670. Min Act: -0.1700
Data Index: 898256 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3858. Min Range: -4.3858
Max Act: 4.1983. Min Act: -0.1697
Data Index: 1617178 (Python Code)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3858. Min Range: -4.3858
Max Act: 4.1983. Min Act: -0.1700
Data Index: 721621 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3858. Min Range: -4.3858
Max Act: 4.1670. Min Act: -0.1700
Data Index: 307830 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3858. Min Range: -4.3858
Max Act: 4.0889. Min Act: -0.1700
Data Index: 1342905 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3858. Min Range: -4.3858
Max Act: 4.1670. Min Act: -0.1700
Data Index: 1004153 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3858. Min Range: -4.3858
Max Act: 4.1983. Min Act: -0.1700
Data Index: 884730 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3858. Min Range: -4.3858
Max Act: 4.0732. Min Act: -0.1700
Data Index: 305765 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3858. Min Range: -4.3858
Max Act: 4.1045. Min Act: -0.1700
Data Index: 1527394 (Python Code)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3858. Min Range: -4.3858
Max Act: 4.1045. Min Act: -0.1700
Data Index: 1053284 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3858. Min Range: -4.3858
Max Act: 4.1358. Min Act: -0.1700
Data Index: 1154205 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3858. Min Range: -4.3858
Max Act: 4.0576. Min Act: -0.1700
Data Index: 237140 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3858. Min Range: -4.3858
Max Act: 4.1045. Min Act: -0.1700
Data Index: 693308 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3858. Min Range: -4.3858
Max Act: 4.0420. Min Act: -0.1700
Data Index: 279413 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3858. Min Range: -4.3858
Max Act: 4.0889. Min Act: -0.1700
Data Index: 767081 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19