Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 51 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9055. Min Range: -2.9055
Max Act: 2.9055. Min Act: -0.1700
Data Index: 1022875 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9055. Min Range: -2.9055
Max Act: 2.9055. Min Act: -0.1700
Data Index: 1047544 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9055. Min Range: -2.9055
Max Act: 2.8737. Min Act: -0.1700
Data Index: 958216 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9055. Min Range: -2.9055
Max Act: 2.8419. Min Act: -0.1700
Data Index: 542679 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9055. Min Range: -2.9055
Max Act: 2.8260. Min Act: -0.1700
Data Index: 1265628 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9055. Min Range: -2.9055
Max Act: 2.8101. Min Act: -0.1700
Data Index: 318119 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9055. Min Range: -2.9055
Max Act: 2.8101. Min Act: -0.1700
Data Index: 275957 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9055. Min Range: -2.9055
Max Act: 2.7783. Min Act: -0.1700
Data Index: 547099 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9055. Min Range: -2.9055
Max Act: 2.7942. Min Act: -0.1700
Data Index: 448742 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9055. Min Range: -2.9055
Max Act: 2.7623. Min Act: -0.1700
Data Index: 653621 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9055. Min Range: -2.9055
Max Act: 2.7783. Min Act: -0.1700
Data Index: 756859 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9055. Min Range: -2.9055
Max Act: 2.7464. Min Act: -0.1700
Data Index: 510034 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9055. Min Range: -2.9055
Max Act: 2.7623. Min Act: -0.1700
Data Index: 324379 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9055. Min Range: -2.9055
Max Act: 2.7464. Min Act: -0.1700
Data Index: 1121111 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9055. Min Range: -2.9055
Max Act: 2.7464. Min Act: -0.1700
Data Index: 1276875 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9055. Min Range: -2.9055
Max Act: 2.7623. Min Act: -0.1700
Data Index: 1126945 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9055. Min Range: -2.9055
Max Act: 2.7464. Min Act: -0.1700
Data Index: 1274161 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9055. Min Range: -2.9055
Max Act: 2.7304. Min Act: -0.1700
Data Index: 646566 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9055. Min Range: -2.9055
Max Act: 2.7464. Min Act: -0.1700
Data Index: 433925 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9055. Min Range: -2.9055
Max Act: 2.7304. Min Act: -0.1700
Data Index: 436451 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19