Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1955 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4919. Min Range: -2.4919
Max Act: 2.4919. Min Act: -0.1700
Data Index: 1241616 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4919. Min Range: -2.4919
Max Act: 2.4107. Min Act: -0.1700
Data Index: 464180 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4919. Min Range: -2.4919
Max Act: 2.3944. Min Act: -0.1700
Data Index: 1374084 (Python Code)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4919. Min Range: -2.4919
Max Act: 2.3944. Min Act: -0.1700
Data Index: 1594115 (Python Code)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4919. Min Range: -2.4919
Max Act: 2.3780. Min Act: -0.1700
Data Index: 1357607 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4919. Min Range: -2.4919
Max Act: 2.3780. Min Act: -0.1700
Data Index: 864470 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4919. Min Range: -2.4919
Max Act: 2.3617. Min Act: -0.1700
Data Index: 223031 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4919. Min Range: -2.4919
Max Act: 2.3617. Min Act: -0.1700
Data Index: 99730 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4919. Min Range: -2.4919
Max Act: 2.3289. Min Act: -0.1700
Data Index: 610588 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4919. Min Range: -2.4919
Max Act: 2.3289. Min Act: -0.1700
Data Index: 1329262 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4919. Min Range: -2.4919
Max Act: 2.3289. Min Act: -0.1700
Data Index: 1137370 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4919. Min Range: -2.4919
Max Act: 2.3125. Min Act: -0.1700
Data Index: 1351704 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4919. Min Range: -2.4919
Max Act: 2.2961. Min Act: -0.1700
Data Index: 1579341 (Python Code)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4919. Min Range: -2.4919
Max Act: 2.2961. Min Act: -0.1700
Data Index: 509002 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4919. Min Range: -2.4919
Max Act: 2.2961. Min Act: -0.1700
Data Index: 739367 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4919. Min Range: -2.4919
Max Act: 2.2961. Min Act: -0.1700
Data Index: 249705 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4919. Min Range: -2.4919
Max Act: 2.2796. Min Act: -0.1700
Data Index: 952011 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4919. Min Range: -2.4919
Max Act: 2.2796. Min Act: -0.1700
Data Index: 255745 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4919. Min Range: -2.4919
Max Act: 2.2796. Min Act: -0.1700
Data Index: 1065282 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4919. Min Range: -2.4919
Max Act: 2.2796. Min Act: -0.1700
Data Index: 689351 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19