Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 143 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9138. Min Range: -2.9138
Max Act: 2.9138. Min Act: -0.1700
Data Index: 754818 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9138. Min Range: -2.9138
Max Act: 2.8979. Min Act: -0.1700
Data Index: 1484546 (Python Code)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9138. Min Range: -2.9138
Max Act: 2.9138. Min Act: -0.1700
Data Index: 729550 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9138. Min Range: -2.9138
Max Act: 2.9138. Min Act: -0.1700
Data Index: 688620 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9138. Min Range: -2.9138
Max Act: 2.8821. Min Act: -0.1700
Data Index: 770443 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9138. Min Range: -2.9138
Max Act: 2.8979. Min Act: -0.1700
Data Index: 349978 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9138. Min Range: -2.9138
Max Act: 2.8662. Min Act: -0.1700
Data Index: 1413074 (Python Code)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9138. Min Range: -2.9138
Max Act: 2.8662. Min Act: -0.1700
Data Index: 1405106 (Python Code)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9138. Min Range: -2.9138
Max Act: 2.8662. Min Act: -0.1700
Data Index: 1301701 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9138. Min Range: -2.9138
Max Act: 2.8662. Min Act: -0.1700
Data Index: 907482 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9138. Min Range: -2.9138
Max Act: 2.8662. Min Act: -0.1700
Data Index: 1064711 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9138. Min Range: -2.9138
Max Act: 2.8821. Min Act: -0.1700
Data Index: 103166 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9138. Min Range: -2.9138
Max Act: 2.8821. Min Act: -0.1700
Data Index: 1219054 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9138. Min Range: -2.9138
Max Act: 2.8821. Min Act: -0.1700
Data Index: 304957 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9138. Min Range: -2.9138
Max Act: 2.8821. Min Act: -0.1700
Data Index: 592416 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9138. Min Range: -2.9138
Max Act: 2.8503. Min Act: -0.1700
Data Index: 1350691 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9138. Min Range: -2.9138
Max Act: 2.8662. Min Act: -0.1700
Data Index: 25210 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9138. Min Range: -2.9138
Max Act: 2.8662. Min Act: -0.1700
Data Index: 647215 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9138. Min Range: -2.9138
Max Act: 2.8662. Min Act: -0.1699
Data Index: 1586692 (Python Code)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9138. Min Range: -2.9138
Max Act: 2.8503. Min Act: -0.1700
Data Index: 1608055 (Python Code)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19