Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 900 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9397. Min Range: -4.9397
Max Act: 4.9397. Min Act: -0.1700
Data Index: 632697 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9397. Min Range: -4.9397
Max Act: 4.8459. Min Act: -0.1700
Data Index: 456549 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9397. Min Range: -4.9397
Max Act: 4.8772. Min Act: -0.1700
Data Index: 1183533 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9397. Min Range: -4.9397
Max Act: 4.8459. Min Act: -0.1700
Data Index: 1155663 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9397. Min Range: -4.9397
Max Act: 4.8147. Min Act: -0.1700
Data Index: 1400602 (Python Code)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9397. Min Range: -4.9397
Max Act: 4.8147. Min Act: -0.1700
Data Index: 842693 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9397. Min Range: -4.9397
Max Act: 4.7834. Min Act: -0.1700
Data Index: 203532 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9397. Min Range: -4.9397
Max Act: 4.7834. Min Act: -0.1700
Data Index: 200918 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9397. Min Range: -4.9397
Max Act: 4.8147. Min Act: -0.1700
Data Index: 812659 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9397. Min Range: -4.9397
Max Act: 4.7834. Min Act: -0.1700
Data Index: 828541 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9397. Min Range: -4.9397
Max Act: 4.7834. Min Act: -0.1700
Data Index: 1063179 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9397. Min Range: -4.9397
Max Act: 4.7522. Min Act: -0.1700
Data Index: 93095 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9397. Min Range: -4.9397
Max Act: 4.8147. Min Act: -0.1700
Data Index: 1419039 (Python Code)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9397. Min Range: -4.9397
Max Act: 4.7522. Min Act: -0.1700
Data Index: 1379657 (Python Code)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9397. Min Range: -4.9397
Max Act: 4.7834. Min Act: -0.1700
Data Index: 1564203 (Python Code)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9397. Min Range: -4.9397
Max Act: 4.7834. Min Act: -0.1700
Data Index: 797964 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9397. Min Range: -4.9397
Max Act: 4.7834. Min Act: -0.1699
Data Index: 952500 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9397. Min Range: -4.9397
Max Act: 4.7522. Min Act: -0.1700
Data Index: 40767 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9397. Min Range: -4.9397
Max Act: 4.7834. Min Act: -0.1700
Data Index: 1140063 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9397. Min Range: -4.9397
Max Act: 4.7522. Min Act: -0.1700
Data Index: 922787 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19