Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 86 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.5961. Min Range: -3.5961
Max Act: 3.5961. Min Act: -0.1700
Data Index: 667681 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5961. Min Range: -3.5961
Max Act: 3.3296. Min Act: -0.1700
Data Index: 1070315 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5961. Min Range: -3.5961
Max Act: 3.0937. Min Act: -0.1700
Data Index: 1114132 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5961. Min Range: -3.5961
Max Act: 2.9039. Min Act: -0.1700
Data Index: 1351917 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5961. Min Range: -3.5961
Max Act: 2.9039. Min Act: -0.1700
Data Index: 393875 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5961. Min Range: -3.5961
Max Act: 2.9039. Min Act: -0.1700
Data Index: 704182 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5961. Min Range: -3.5961
Max Act: 2.8881. Min Act: -0.1700
Data Index: 394718 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5961. Min Range: -3.5961
Max Act: 2.8722. Min Act: -0.1700
Data Index: 1545901 (Python Code)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5961. Min Range: -3.5961
Max Act: 2.8722. Min Act: -0.1699
Data Index: 59493 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5961. Min Range: -3.5961
Max Act: 2.8722. Min Act: -0.1700
Data Index: 550615 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5961. Min Range: -3.5961
Max Act: 2.8722. Min Act: -0.1700
Data Index: 276139 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5961. Min Range: -3.5961
Max Act: 2.8722. Min Act: -0.1700
Data Index: 840962 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5961. Min Range: -3.5961
Max Act: 2.8722. Min Act: -0.1700
Data Index: 914437 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5961. Min Range: -3.5961
Max Act: 2.8563. Min Act: -0.1700
Data Index: 861477 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5961. Min Range: -3.5961
Max Act: 2.8722. Min Act: -0.1700
Data Index: 1138071 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5961. Min Range: -3.5961
Max Act: 2.8722. Min Act: -0.1700
Data Index: 673983 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5961. Min Range: -3.5961
Max Act: 2.8404. Min Act: -0.1700
Data Index: 613474 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5961. Min Range: -3.5961
Max Act: 2.8563. Min Act: -0.1700
Data Index: 1276748 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5961. Min Range: -3.5961
Max Act: 2.8404. Min Act: -0.1700
Data Index: 277573 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5961. Min Range: -3.5961
Max Act: 2.8404. Min Act: -0.1700
Data Index: 539260 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19