Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 866 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7078. Min Range: -2.7078
Max Act: 2.7078. Min Act: -0.1700
Data Index: 1338768 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7078. Min Range: -2.7078
Max Act: 2.6758. Min Act: -0.1700
Data Index: 589707 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7078. Min Range: -2.7078
Max Act: 2.6918. Min Act: -0.1700
Data Index: 175577 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7078. Min Range: -2.7078
Max Act: 2.6918. Min Act: -0.1700
Data Index: 122158 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7078. Min Range: -2.7078
Max Act: 2.6918. Min Act: -0.1700
Data Index: 847660 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7078. Min Range: -2.7078
Max Act: 2.6598. Min Act: -0.1700
Data Index: 1139361 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7078. Min Range: -2.7078
Max Act: 2.6598. Min Act: -0.1700
Data Index: 189080 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7078. Min Range: -2.7078
Max Act: 2.6758. Min Act: -0.1700
Data Index: 782692 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7078. Min Range: -2.7078
Max Act: 2.6598. Min Act: -0.1700
Data Index: 796987 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7078. Min Range: -2.7078
Max Act: 2.6598. Min Act: -0.1700
Data Index: 1134983 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7078. Min Range: -2.7078
Max Act: 2.6437. Min Act: -0.1700
Data Index: 989650 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7078. Min Range: -2.7078
Max Act: 2.6598. Min Act: -0.1700
Data Index: 1252847 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7078. Min Range: -2.7078
Max Act: 2.6598. Min Act: -0.1700
Data Index: 912549 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7078. Min Range: -2.7078
Max Act: 2.6437. Min Act: -0.1700
Data Index: 1115629 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7078. Min Range: -2.7078
Max Act: 2.6116. Min Act: -0.1699
Data Index: 1072732 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7078. Min Range: -2.7078
Max Act: 2.6277. Min Act: -0.1700
Data Index: 86949 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7078. Min Range: -2.7078
Max Act: 2.6277. Min Act: -0.1700
Data Index: 575576 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7078. Min Range: -2.7078
Max Act: 2.6277. Min Act: -0.1699
Data Index: 629159 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7078. Min Range: -2.7078
Max Act: 2.6116. Min Act: -0.1700
Data Index: 169436 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7078. Min Range: -2.7078
Max Act: 2.6116. Min Act: -0.1700
Data Index: 50071 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19