Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 247 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.5170. Min Range: -2.5170
Max Act: 2.5170. Min Act: -0.1700
Data Index: 1569815 (Python Code)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5170. Min Range: -2.5170
Max Act: 2.5008. Min Act: -0.1700
Data Index: 1276010 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5170. Min Range: -2.5170
Max Act: 2.4846. Min Act: -0.1700
Data Index: 1563431 (Python Code)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5170. Min Range: -2.5170
Max Act: 2.5170. Min Act: -0.1700
Data Index: 942875 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5170. Min Range: -2.5170
Max Act: 2.4683. Min Act: -0.1700
Data Index: 1581078 (Python Code)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5170. Min Range: -2.5170
Max Act: 2.4846. Min Act: -0.1700
Data Index: 1510413 (Python Code)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5170. Min Range: -2.5170
Max Act: 2.4846. Min Act: -0.1700
Data Index: 1344301 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5170. Min Range: -2.5170
Max Act: 2.4846. Min Act: -0.1700
Data Index: 317594 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5170. Min Range: -2.5170
Max Act: 2.4683. Min Act: -0.1700
Data Index: 302071 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5170. Min Range: -2.5170
Max Act: 2.4683. Min Act: -0.1700
Data Index: 618943 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5170. Min Range: -2.5170
Max Act: 2.4358. Min Act: -0.1700
Data Index: 1644484 (Python Code)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5170. Min Range: -2.5170
Max Act: 2.4521. Min Act: -0.1700
Data Index: 1482004 (Python Code)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5170. Min Range: -2.5170
Max Act: 2.4521. Min Act: -0.1700
Data Index: 1473102 (Python Code)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5170. Min Range: -2.5170
Max Act: 2.4358. Min Act: -0.1700
Data Index: 481135 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5170. Min Range: -2.5170
Max Act: 2.4521. Min Act: -0.1700
Data Index: 802941 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5170. Min Range: -2.5170
Max Act: 2.4358. Min Act: -0.1700
Data Index: 420601 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5170. Min Range: -2.5170
Max Act: 2.4358. Min Act: -0.1700
Data Index: 1165284 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5170. Min Range: -2.5170
Max Act: 2.4521. Min Act: -0.1700
Data Index: 1309153 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5170. Min Range: -2.5170
Max Act: 2.4521. Min Act: -0.1700
Data Index: 991024 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5170. Min Range: -2.5170
Max Act: 2.4358. Min Act: -0.1700
Data Index: 2701 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19