Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1924 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5746. Min Range: -2.5746
Max Act: 2.5746. Min Act: -0.1700
Data Index: 22936 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5746. Min Range: -2.5746
Max Act: 2.5746. Min Act: -0.1700
Data Index: 349816 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5746. Min Range: -2.5746
Max Act: 2.5585. Min Act: -0.1700
Data Index: 1225478 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5746. Min Range: -2.5746
Max Act: 2.4776. Min Act: -0.1700
Data Index: 1284141 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5746. Min Range: -2.5746
Max Act: 2.4938. Min Act: -0.1700
Data Index: 360708 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5746. Min Range: -2.5746
Max Act: 2.4776. Min Act: -0.1700
Data Index: 1184187 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5746. Min Range: -2.5746
Max Act: 2.4614. Min Act: -0.1700
Data Index: 190821 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5746. Min Range: -2.5746
Max Act: 2.4451. Min Act: -0.1700
Data Index: 58230 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5746. Min Range: -2.5746
Max Act: 2.3799. Min Act: -0.1700
Data Index: 816661 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5746. Min Range: -2.5746
Max Act: 2.3799. Min Act: -0.1700
Data Index: 577156 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5746. Min Range: -2.5746
Max Act: 2.3963. Min Act: -0.1700
Data Index: 244357 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5746. Min Range: -2.5746
Max Act: 2.3636. Min Act: -0.1700
Data Index: 285641 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5746. Min Range: -2.5746
Max Act: 2.3636. Min Act: -0.1700
Data Index: 544381 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5746. Min Range: -2.5746
Max Act: 2.3636. Min Act: -0.1700
Data Index: 1313341 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5746. Min Range: -2.5746
Max Act: 2.3636. Min Act: -0.1700
Data Index: 900316 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5746. Min Range: -2.5746
Max Act: 2.3472. Min Act: -0.1700
Data Index: 798875 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5746. Min Range: -2.5746
Max Act: 2.3472. Min Act: -0.1700
Data Index: 481754 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5746. Min Range: -2.5746
Max Act: 2.3308. Min Act: -0.1700
Data Index: 958942 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5746. Min Range: -2.5746
Max Act: 2.3472. Min Act: -0.1700
Data Index: 322291 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5746. Min Range: -2.5746
Max Act: 2.3308. Min Act: -0.1700
Data Index: 1607748 (Python Code)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19