Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1918 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.0396. Min Range: -2.0396
Max Act: 2.0396. Min Act: -0.1700
Data Index: 195438 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0396. Min Range: -2.0396
Max Act: 1.9552. Min Act: -0.1700
Data Index: 898932 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0396. Min Range: -2.0396
Max Act: 1.9382. Min Act: -0.1700
Data Index: 1173057 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0396. Min Range: -2.0396
Max Act: 1.9212. Min Act: -0.1700
Data Index: 1313215 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0396. Min Range: -2.0396
Max Act: 1.9212. Min Act: -0.1700
Data Index: 1345579 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0396. Min Range: -2.0396
Max Act: 1.9212. Min Act: -0.1700
Data Index: 304361 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0396. Min Range: -2.0396
Max Act: 1.9042. Min Act: -0.1699
Data Index: 948815 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0396. Min Range: -2.0396
Max Act: 1.8871. Min Act: -0.1700
Data Index: 1284104 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0396. Min Range: -2.0396
Max Act: 1.8871. Min Act: -0.1700
Data Index: 816538 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0396. Min Range: -2.0396
Max Act: 1.8871. Min Act: -0.1700
Data Index: 581803 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0396. Min Range: -2.0396
Max Act: 1.8871. Min Act: -0.1700
Data Index: 886657 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0396. Min Range: -2.0396
Max Act: 1.8871. Min Act: -0.1700
Data Index: 626358 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0396. Min Range: -2.0396
Max Act: 1.8871. Min Act: -0.1700
Data Index: 218285 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0396. Min Range: -2.0396
Max Act: 1.8700. Min Act: -0.1700
Data Index: 129912 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0396. Min Range: -2.0396
Max Act: 1.8871. Min Act: -0.1700
Data Index: 741655 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0396. Min Range: -2.0396
Max Act: 1.8871. Min Act: -0.1700
Data Index: 341128 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0396. Min Range: -2.0396
Max Act: 1.8871. Min Act: -0.1699
Data Index: 651534 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0396. Min Range: -2.0396
Max Act: 1.8529. Min Act: -0.1700
Data Index: 1052650 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0396. Min Range: -2.0396
Max Act: 1.8700. Min Act: -0.1700
Data Index: 1166062 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0396. Min Range: -2.0396
Max Act: 1.8700. Min Act: -0.1699
Data Index: 1177269 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19