Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 814 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.1174. Min Range: -3.1174
Max Act: 3.1174. Min Act: -0.1700
Data Index: 863512 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1174. Min Range: -3.1174
Max Act: 2.9911. Min Act: -0.1700
Data Index: 140876 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1174. Min Range: -3.1174
Max Act: 2.9120. Min Act: -0.1700
Data Index: 120512 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1174. Min Range: -3.1174
Max Act: 2.8326. Min Act: -0.1700
Data Index: 1122149 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1174. Min Range: -3.1174
Max Act: 2.8326. Min Act: -0.1700
Data Index: 13907 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1174. Min Range: -3.1174
Max Act: 2.8326. Min Act: -0.1700
Data Index: 200456 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1174. Min Range: -3.1174
Max Act: 2.8485. Min Act: -0.1700
Data Index: 303109 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1174. Min Range: -3.1174
Max Act: 2.8485. Min Act: -0.1700
Data Index: 1357603 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1174. Min Range: -3.1174
Max Act: 2.8008. Min Act: -0.1700
Data Index: 319106 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1174. Min Range: -3.1174
Max Act: 2.8008. Min Act: -0.1700
Data Index: 740542 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1174. Min Range: -3.1174
Max Act: 2.8167. Min Act: -0.1700
Data Index: 622114 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1174. Min Range: -3.1174
Max Act: 2.7848. Min Act: -0.1700
Data Index: 1018688 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1174. Min Range: -3.1174
Max Act: 2.8326. Min Act: -0.1700
Data Index: 951002 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1174. Min Range: -3.1174
Max Act: 2.7529. Min Act: -0.1700
Data Index: 591476 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1174. Min Range: -3.1174
Max Act: 2.7848. Min Act: -0.1700
Data Index: 564584 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1174. Min Range: -3.1174
Max Act: 2.7689. Min Act: -0.1700
Data Index: 779066 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1174. Min Range: -3.1174
Max Act: 2.7689. Min Act: -0.1700
Data Index: 650573 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1174. Min Range: -3.1174
Max Act: 2.8167. Min Act: -0.1700
Data Index: 175426 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1174. Min Range: -3.1174
Max Act: 2.7689. Min Act: -0.1700
Data Index: 426245 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1174. Min Range: -3.1174
Max Act: 2.7689. Min Act: -0.1700
Data Index: 878084 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19