Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1285 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9153. Min Range: -2.9153
Max Act: 2.9153. Min Act: -0.1700
Data Index: 1154771 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9153. Min Range: -2.9153
Max Act: 2.8677. Min Act: -0.1700
Data Index: 1586153 (Python Code)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9153. Min Range: -2.9153
Max Act: 2.8519. Min Act: -0.1700
Data Index: 289173 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9153. Min Range: -2.9153
Max Act: 2.8519. Min Act: -0.1700
Data Index: 1359200 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9153. Min Range: -2.9153
Max Act: 2.8041. Min Act: -0.1700
Data Index: 458581 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9153. Min Range: -2.9153
Max Act: 2.8201. Min Act: -0.1700
Data Index: 411326 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9153. Min Range: -2.9153
Max Act: 2.8041. Min Act: -0.1700
Data Index: 716336 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9153. Min Range: -2.9153
Max Act: 2.8041. Min Act: -0.1700
Data Index: 436568 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9153. Min Range: -2.9153
Max Act: 2.7882. Min Act: -0.1700
Data Index: 931524 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9153. Min Range: -2.9153
Max Act: 2.7723. Min Act: -0.1700
Data Index: 479005 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9153. Min Range: -2.9153
Max Act: 2.7723. Min Act: -0.1700
Data Index: 486961 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9153. Min Range: -2.9153
Max Act: 2.7723. Min Act: -0.1700
Data Index: 51958 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9153. Min Range: -2.9153
Max Act: 2.7723. Min Act: -0.1700
Data Index: 691246 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9153. Min Range: -2.9153
Max Act: 2.7563. Min Act: -0.1700
Data Index: 965200 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9153. Min Range: -2.9153
Max Act: 2.7723. Min Act: -0.1700
Data Index: 764233 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9153. Min Range: -2.9153
Max Act: 2.7404. Min Act: -0.1700
Data Index: 167185 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9153. Min Range: -2.9153
Max Act: 2.7563. Min Act: -0.1700
Data Index: 97102 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9153. Min Range: -2.9153
Max Act: 2.7404. Min Act: -0.1700
Data Index: 23317 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9153. Min Range: -2.9153
Max Act: 2.7563. Min Act: -0.1700
Data Index: 1133115 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9153. Min Range: -2.9153
Max Act: 2.7404. Min Act: -0.1700
Data Index: 1633157 (Python Code)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19