Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1887 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.1105. Min Range: -2.1105
Max Act: 2.1105. Min Act: -0.1700
Data Index: 1178298 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1105. Min Range: -2.1105
Max Act: 2.0770. Min Act: -0.1700
Data Index: 1243986 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1105. Min Range: -2.1105
Max Act: 2.0602. Min Act: -0.1700
Data Index: 587908 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1105. Min Range: -2.1105
Max Act: 2.0097. Min Act: -0.1700
Data Index: 500313 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1105. Min Range: -2.1105
Max Act: 2.0266. Min Act: -0.1700
Data Index: 1113765 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1105. Min Range: -2.1105
Max Act: 2.0097. Min Act: -0.1700
Data Index: 1512473 (Python Code)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9929. Min Act: -0.1700
Data Index: 630091 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9929. Min Act: -0.1700
Data Index: 860855 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1105. Min Range: -2.1105
Max Act: 2.0097. Min Act: -0.1700
Data Index: 746402 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9929. Min Act: -0.1700
Data Index: 561493 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9929. Min Act: -0.1700
Data Index: 645223 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9929. Min Act: -0.1700
Data Index: 1119853 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9590. Min Act: -0.1700
Data Index: 484102 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9759. Min Act: -0.1700
Data Index: 1318745 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9759. Min Act: -0.1700
Data Index: 1441782 (Python Code)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9590. Min Act: -0.1700
Data Index: 560866 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9590. Min Act: -0.1700
Data Index: 707376 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9590. Min Act: -0.1700
Data Index: 469094 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9590. Min Act: -0.1700
Data Index: 1005030 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9251. Min Act: -0.1700
Data Index: 440698 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19