Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1789 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.0723. Min Range: -3.0723
Max Act: 3.0723. Min Act: -0.1700
Data Index: 1177903 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0723. Min Range: -3.0723
Max Act: 2.9459. Min Act: -0.1700
Data Index: 1069826 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0723. Min Range: -3.0723
Max Act: 2.9459. Min Act: -0.1700
Data Index: 7034 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0723. Min Range: -3.0723
Max Act: 2.9142. Min Act: -0.1700
Data Index: 476255 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0723. Min Range: -3.0723
Max Act: 2.8983. Min Act: -0.1700
Data Index: 56176 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0723. Min Range: -3.0723
Max Act: 2.8666. Min Act: -0.1700
Data Index: 676957 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0723. Min Range: -3.0723
Max Act: 2.8507. Min Act: -0.1700
Data Index: 1388035 (Python Code)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0723. Min Range: -3.0723
Max Act: 2.8348. Min Act: -0.1700
Data Index: 537014 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0723. Min Range: -3.0723
Max Act: 2.8189. Min Act: -0.1700
Data Index: 1009832 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0723. Min Range: -3.0723
Max Act: 2.8189. Min Act: -0.1700
Data Index: 585583 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0723. Min Range: -3.0723
Max Act: 2.8189. Min Act: -0.1700
Data Index: 609302 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0723. Min Range: -3.0723
Max Act: 2.8189. Min Act: -0.1700
Data Index: 626864 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0723. Min Range: -3.0723
Max Act: 2.8189. Min Act: -0.1700
Data Index: 388984 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0723. Min Range: -3.0723
Max Act: 2.8189. Min Act: -0.1700
Data Index: 710712 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0723. Min Range: -3.0723
Max Act: 2.8189. Min Act: -0.1700
Data Index: 13593 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0723. Min Range: -3.0723
Max Act: 2.8030. Min Act: -0.1700
Data Index: 517396 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0723. Min Range: -3.0723
Max Act: 2.8030. Min Act: -0.1700
Data Index: 412706 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0723. Min Range: -3.0723
Max Act: 2.8030. Min Act: -0.1700
Data Index: 1180178 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0723. Min Range: -3.0723
Max Act: 2.7870. Min Act: -0.1700
Data Index: 525299 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0723. Min Range: -3.0723
Max Act: 2.7870. Min Act: -0.1700
Data Index: 154764 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19