Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 814 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.9532. Min Range: -4.9532
Max Act: 4.9532. Min Act: -0.1700
Data Index: 463392 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9532. Min Range: -4.9532
Max Act: 4.8594. Min Act: -0.1700
Data Index: 926502 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9532. Min Range: -4.9532
Max Act: 4.8594. Min Act: -0.1700
Data Index: 433406 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9532. Min Range: -4.9532
Max Act: 4.8594. Min Act: -0.1700
Data Index: 865203 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9532. Min Range: -4.9532
Max Act: 4.7344. Min Act: -0.1700
Data Index: 886010 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9532. Min Range: -4.9532
Max Act: 4.8282. Min Act: -0.1700
Data Index: 31750 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9532. Min Range: -4.9532
Max Act: 4.7969. Min Act: -0.1700
Data Index: 605464 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9532. Min Range: -4.9532
Max Act: 4.7969. Min Act: -0.1700
Data Index: 659933 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9532. Min Range: -4.9532
Max Act: 4.7657. Min Act: -0.1700
Data Index: 1103246 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9532. Min Range: -4.9532
Max Act: 4.7031. Min Act: -0.1700
Data Index: 395230 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9532. Min Range: -4.9532
Max Act: 4.7657. Min Act: -0.1700
Data Index: 754965 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9532. Min Range: -4.9532
Max Act: 4.7657. Min Act: -0.1700
Data Index: 1329458 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9532. Min Range: -4.9532
Max Act: 4.7344. Min Act: -0.1700
Data Index: 1275499 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9532. Min Range: -4.9532
Max Act: 4.7031. Min Act: -0.1700
Data Index: 558267 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9532. Min Range: -4.9532
Max Act: 4.7031. Min Act: -0.1700
Data Index: 1321415 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9532. Min Range: -4.9532
Max Act: 4.7031. Min Act: -0.1700
Data Index: 326503 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9532. Min Range: -4.9532
Max Act: 4.7031. Min Act: -0.1700
Data Index: 1132794 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9532. Min Range: -4.9532
Max Act: 4.7031. Min Act: -0.1700
Data Index: 31054 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9532. Min Range: -4.9532
Max Act: 4.7031. Min Act: -0.1700
Data Index: 418215 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9532. Min Range: -4.9532
Max Act: 4.7031. Min Act: -0.1700
Data Index: 173980 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19