Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 229 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.7663. Min Range: -6.7663
Max Act: 6.7663. Min Act: -0.1700
Data Index: 446992 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7663. Min Range: -6.7663
Max Act: 6.6725. Min Act: -0.1700
Data Index: 15012 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7663. Min Range: -6.7663
Max Act: 6.6725. Min Act: -0.1700
Data Index: 1600938 (Python Code)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7663. Min Range: -6.7663
Max Act: 6.6413. Min Act: -0.1700
Data Index: 1103120 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7663. Min Range: -6.7663
Max Act: 6.6725. Min Act: -0.1700
Data Index: 928755 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7663. Min Range: -6.7663
Max Act: 6.6100. Min Act: -0.1700
Data Index: 1129634 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7663. Min Range: -6.7663
Max Act: 6.5788. Min Act: -0.1700
Data Index: 764708 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7663. Min Range: -6.7663
Max Act: 6.5788. Min Act: -0.1700
Data Index: 1598450 (Python Code)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7663. Min Range: -6.7663
Max Act: 6.4850. Min Act: -0.1700
Data Index: 711104 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7663. Min Range: -6.7663
Max Act: 6.6100. Min Act: -0.1700
Data Index: 1076235 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7663. Min Range: -6.7663
Max Act: 6.4850. Min Act: -0.1700
Data Index: 900683 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7663. Min Range: -6.7663
Max Act: 6.5475. Min Act: -0.1700
Data Index: 335390 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7663. Min Range: -6.7663
Max Act: 6.5163. Min Act: -0.1700
Data Index: 1187229 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7663. Min Range: -6.7663
Max Act: 6.4225. Min Act: -0.1700
Data Index: 801261 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7663. Min Range: -6.7663
Max Act: 6.4225. Min Act: -0.1700
Data Index: 862983 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7663. Min Range: -6.7663
Max Act: 6.4225. Min Act: -0.1700
Data Index: 540879 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7663. Min Range: -6.7663
Max Act: 6.3913. Min Act: -0.1700
Data Index: 1032682 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7663. Min Range: -6.7663
Max Act: 6.5475. Min Act: -0.1700
Data Index: 1044731 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7663. Min Range: -6.7663
Max Act: 6.4538. Min Act: -0.1700
Data Index: 1249204 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7663. Min Range: -6.7663
Max Act: 6.3600. Min Act: -0.1700
Data Index: 392001 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19