Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2024 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.1866. Min Range: -2.1866
Max Act: 2.1866. Min Act: -0.1700
Data Index: 61703 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1866. Min Range: -2.1866
Max Act: 2.1699. Min Act: -0.1700
Data Index: 230192 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1866. Min Range: -2.1866
Max Act: 2.1199. Min Act: -0.1700
Data Index: 1015249 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1866. Min Range: -2.1866
Max Act: 2.1366. Min Act: -0.1700
Data Index: 498655 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1866. Min Range: -2.1866
Max Act: 2.1366. Min Act: -0.1700
Data Index: 845846 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1866. Min Range: -2.1866
Max Act: 2.1032. Min Act: -0.1700
Data Index: 496232 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1866. Min Range: -2.1866
Max Act: 2.1199. Min Act: -0.1700
Data Index: 1227812 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1866. Min Range: -2.1866
Max Act: 2.1032. Min Act: -0.1700
Data Index: 42230 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1866. Min Range: -2.1866
Max Act: 2.0865. Min Act: -0.1700
Data Index: 366987 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1866. Min Range: -2.1866
Max Act: 2.1032. Min Act: -0.1700
Data Index: 54407 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1866. Min Range: -2.1866
Max Act: 2.0865. Min Act: -0.1700
Data Index: 1281160 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1866. Min Range: -2.1866
Max Act: 2.0697. Min Act: -0.1700
Data Index: 851470 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1866. Min Range: -2.1866
Max Act: 2.0529. Min Act: -0.1700
Data Index: 1110149 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1866. Min Range: -2.1866
Max Act: 2.0697. Min Act: -0.1700
Data Index: 115825 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1866. Min Range: -2.1866
Max Act: 2.0865. Min Act: -0.1700
Data Index: 864555 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1866. Min Range: -2.1866
Max Act: 2.0529. Min Act: -0.1700
Data Index: 1185208 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1866. Min Range: -2.1866
Max Act: 2.0697. Min Act: -0.1700
Data Index: 1070149 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1866. Min Range: -2.1866
Max Act: 2.0697. Min Act: -0.1700
Data Index: 662732 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1866. Min Range: -2.1866
Max Act: 2.0529. Min Act: -0.1700
Data Index: 1340425 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1866. Min Range: -2.1866
Max Act: 2.0697. Min Act: -0.1700
Data Index: 797734 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19