Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1915 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8110. Min Range: -2.8110
Max Act: 2.8110. Min Act: -0.1700
Data Index: 497126 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8110. Min Range: -2.8110
Max Act: 2.8110. Min Act: -0.1700
Data Index: 832598 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8110. Min Range: -2.8110
Max Act: 2.7951. Min Act: -0.1700
Data Index: 851198 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8110. Min Range: -2.8110
Max Act: 2.7951. Min Act: -0.1700
Data Index: 742106 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8110. Min Range: -2.8110
Max Act: 2.7951. Min Act: -0.1700
Data Index: 1104599 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8110. Min Range: -2.8110
Max Act: 2.7951. Min Act: -0.1700
Data Index: 599577 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8110. Min Range: -2.8110
Max Act: 2.7632. Min Act: -0.1700
Data Index: 1372 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8110. Min Range: -2.8110
Max Act: 2.7792. Min Act: -0.1700
Data Index: 420079 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8110. Min Range: -2.8110
Max Act: 2.7792. Min Act: -0.1700
Data Index: 73882 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8110. Min Range: -2.8110
Max Act: 2.7792. Min Act: -0.1700
Data Index: 55939 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8110. Min Range: -2.8110
Max Act: 2.7792. Min Act: -0.1700
Data Index: 1194737 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8110. Min Range: -2.8110
Max Act: 2.7632. Min Act: -0.1700
Data Index: 501406 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8110. Min Range: -2.8110
Max Act: 2.7792. Min Act: -0.1700
Data Index: 90284 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8110. Min Range: -2.8110
Max Act: 2.7951. Min Act: -0.1700
Data Index: 671061 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8110. Min Range: -2.8110
Max Act: 2.7632. Min Act: -0.1700
Data Index: 1176646 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8110. Min Range: -2.8110
Max Act: 2.7632. Min Act: -0.1700
Data Index: 903928 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8110. Min Range: -2.8110
Max Act: 2.7473. Min Act: -0.1700
Data Index: 204402 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8110. Min Range: -2.8110
Max Act: 2.7632. Min Act: -0.1700
Data Index: 774372 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8110. Min Range: -2.8110
Max Act: 2.7632. Min Act: -0.1700
Data Index: 1284045 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8110. Min Range: -2.8110
Max Act: 2.7632. Min Act: -0.1700
Data Index: 230512 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19