Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 244 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8018. Min Range: -2.8018
Max Act: 2.8018. Min Act: -0.1700
Data Index: 403865 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8018. Min Range: -2.8018
Max Act: 2.7540. Min Act: -0.1700
Data Index: 17259 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8018. Min Range: -2.8018
Max Act: 2.7061. Min Act: -0.1700
Data Index: 136472 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8018. Min Range: -2.8018
Max Act: 2.6900. Min Act: -0.1700
Data Index: 978035 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8018. Min Range: -2.8018
Max Act: 2.6420. Min Act: -0.1700
Data Index: 1300258 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8018. Min Range: -2.8018
Max Act: 2.6580. Min Act: -0.1700
Data Index: 1227180 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8018. Min Range: -2.8018
Max Act: 2.6420. Min Act: -0.1700
Data Index: 601519 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8018. Min Range: -2.8018
Max Act: 2.6259. Min Act: -0.1700
Data Index: 981557 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8018. Min Range: -2.8018
Max Act: 2.6098. Min Act: -0.1700
Data Index: 923923 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8018. Min Range: -2.8018
Max Act: 2.6098. Min Act: -0.1700
Data Index: 1018624 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8018. Min Range: -2.8018
Max Act: 2.6098. Min Act: -0.1700
Data Index: 732172 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8018. Min Range: -2.8018
Max Act: 2.5937. Min Act: -0.1700
Data Index: 630859 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8018. Min Range: -2.8018
Max Act: 2.5937. Min Act: -0.1700
Data Index: 62280 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8018. Min Range: -2.8018
Max Act: 2.5776. Min Act: -0.1700
Data Index: 1060896 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8018. Min Range: -2.8018
Max Act: 2.5937. Min Act: -0.1700
Data Index: 234143 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8018. Min Range: -2.8018
Max Act: 2.5937. Min Act: -0.1700
Data Index: 1165949 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8018. Min Range: -2.8018
Max Act: 2.5776. Min Act: -0.1700
Data Index: 704635 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8018. Min Range: -2.8018
Max Act: 2.5937. Min Act: -0.1700
Data Index: 169620 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8018. Min Range: -2.8018
Max Act: 2.5937. Min Act: -0.1700
Data Index: 120748 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8018. Min Range: -2.8018
Max Act: 2.5937. Min Act: -0.1700
Data Index: 1259969 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19