Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 16 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4317. Min Range: -2.4317
Max Act: 2.4317. Min Act: -0.1697
Data Index: 1468585 (Python Code)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4317. Min Range: -2.4317
Max Act: 2.4154. Min Act: -0.1699
Data Index: 1630666 (Python Code)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4317. Min Range: -2.4317
Max Act: 2.3664. Min Act: -0.1700
Data Index: 763183 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4317. Min Range: -2.4317
Max Act: 2.3173. Min Act: -0.1700
Data Index: 1496106 (Python Code)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4317. Min Range: -2.4317
Max Act: 2.2844. Min Act: -0.1700
Data Index: 262042 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4317. Min Range: -2.4317
Max Act: 2.2679. Min Act: -0.1700
Data Index: 552266 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4317. Min Range: -2.4317
Max Act: 2.2679. Min Act: -0.1700
Data Index: 497760 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4317. Min Range: -2.4317
Max Act: 2.2679. Min Act: -0.1700
Data Index: 917764 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4317. Min Range: -2.4317
Max Act: 2.2679. Min Act: -0.1700
Data Index: 413823 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4317. Min Range: -2.4317
Max Act: 2.2679. Min Act: -0.1700
Data Index: 981200 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4317. Min Range: -2.4317
Max Act: 2.2183. Min Act: -0.1700
Data Index: 633349 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4317. Min Range: -2.4317
Max Act: 2.2349. Min Act: -0.1700
Data Index: 1010150 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4317. Min Range: -2.4317
Max Act: 2.2018. Min Act: -0.1700
Data Index: 1241111 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4317. Min Range: -2.4317
Max Act: 2.2018. Min Act: -0.1700
Data Index: 1548495 (Python Code)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4317. Min Range: -2.4317
Max Act: 2.2018. Min Act: -0.1700
Data Index: 794429 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4317. Min Range: -2.4317
Max Act: 2.1852. Min Act: -0.1700
Data Index: 881328 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4317. Min Range: -2.4317
Max Act: 2.1519. Min Act: -0.1700
Data Index: 375114 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4317. Min Range: -2.4317
Max Act: 2.1686. Min Act: -0.1700
Data Index: 498918 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4317. Min Range: -2.4317
Max Act: 2.1852. Min Act: -0.1700
Data Index: 1379257 (Python Code)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4317. Min Range: -2.4317
Max Act: 2.1519. Min Act: -0.1699
Data Index: 1513611 (Python Code)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19