Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1912 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1604. Min Range: -4.1604
Max Act: 4.1604. Min Act: -0.1700
Data Index: 926849 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1604. Min Range: -4.1604
Max Act: 4.0354. Min Act: -0.1700
Data Index: 1193825 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1604. Min Range: -4.1604
Max Act: 4.0354. Min Act: -0.1700
Data Index: 1172943 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1604. Min Range: -4.1604
Max Act: 4.0354. Min Act: -0.1700
Data Index: 689228 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1604. Min Range: -4.1604
Max Act: 3.9416. Min Act: -0.1700
Data Index: 317509 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1604. Min Range: -4.1604
Max Act: 3.9103. Min Act: -0.1700
Data Index: 119236 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1604. Min Range: -4.1604
Max Act: 3.7226. Min Act: -0.1700
Data Index: 675022 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1604. Min Range: -4.1604
Max Act: 3.7852. Min Act: -0.1700
Data Index: 366110 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1604. Min Range: -4.1604
Max Act: 3.8165. Min Act: -0.1700
Data Index: 221316 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1604. Min Range: -4.1604
Max Act: 3.7539. Min Act: -0.1700
Data Index: 122074 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1604. Min Range: -4.1604
Max Act: 3.7852. Min Act: -0.1700
Data Index: 1216954 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1604. Min Range: -4.1604
Max Act: 3.6914. Min Act: -0.1700
Data Index: 329210 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1604. Min Range: -4.1604
Max Act: 3.7539. Min Act: -0.1700
Data Index: 1128733 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1604. Min Range: -4.1604
Max Act: 3.7539. Min Act: -0.1700
Data Index: 10940 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1604. Min Range: -4.1604
Max Act: 3.7226. Min Act: -0.1700
Data Index: 352231 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1604. Min Range: -4.1604
Max Act: 3.7226. Min Act: -0.1700
Data Index: 46935 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1604. Min Range: -4.1604
Max Act: 3.7226. Min Act: -0.1700
Data Index: 760871 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1604. Min Range: -4.1604
Max Act: 3.7226. Min Act: -0.1700
Data Index: 751786 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1604. Min Range: -4.1604
Max Act: 3.6914. Min Act: -0.1700
Data Index: 697269 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1604. Min Range: -4.1604
Max Act: 3.6288. Min Act: -0.1700
Data Index: 1061821 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19