Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2038 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7785. Min Range: -4.7785
Max Act: 4.7785. Min Act: -0.1700
Data Index: 876754 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7785. Min Range: -4.7785
Max Act: 4.5910. Min Act: -0.1700
Data Index: 596002 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7785. Min Range: -4.7785
Max Act: 4.5285. Min Act: -0.1700
Data Index: 105895 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7785. Min Range: -4.7785
Max Act: 4.4347. Min Act: -0.1700
Data Index: 278051 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7785. Min Range: -4.7785
Max Act: 4.4347. Min Act: -0.1700
Data Index: 582925 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7785. Min Range: -4.7785
Max Act: 4.4035. Min Act: -0.1700
Data Index: 528399 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7785. Min Range: -4.7785
Max Act: 4.4035. Min Act: -0.1700
Data Index: 1017254 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7785. Min Range: -4.7785
Max Act: 4.4035. Min Act: -0.1700
Data Index: 189794 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7785. Min Range: -4.7785
Max Act: 4.3409. Min Act: -0.1700
Data Index: 1186634 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7785. Min Range: -4.7785
Max Act: 4.3722. Min Act: -0.1700
Data Index: 1096889 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7785. Min Range: -4.7785
Max Act: 4.3409. Min Act: -0.1700
Data Index: 410315 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7785. Min Range: -4.7785
Max Act: 4.2472. Min Act: -0.1700
Data Index: 90352 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7785. Min Range: -4.7785
Max Act: 4.2784. Min Act: -0.1700
Data Index: 36225 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7785. Min Range: -4.7785
Max Act: 4.1847. Min Act: -0.1700
Data Index: 929163 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7785. Min Range: -4.7785
Max Act: 4.2159. Min Act: -0.1700
Data Index: 271994 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7785. Min Range: -4.7785
Max Act: 4.2472. Min Act: -0.1700
Data Index: 607641 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7785. Min Range: -4.7785
Max Act: 4.2472. Min Act: -0.1700
Data Index: 585481 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7785. Min Range: -4.7785
Max Act: 4.2159. Min Act: -0.1700
Data Index: 640485 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7785. Min Range: -4.7785
Max Act: 4.2159. Min Act: -0.1700
Data Index: 254199 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7785. Min Range: -4.7785
Max Act: 4.2159. Min Act: -0.1700
Data Index: 405146 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19