Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1823 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.0968. Min Range: -3.0968
Max Act: 3.0968. Min Act: -0.1700
Data Index: 328640 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0968. Min Range: -3.0968
Max Act: 2.9546. Min Act: -0.1700
Data Index: 258587 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0968. Min Range: -3.0968
Max Act: 2.9546. Min Act: -0.1700
Data Index: 495629 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0968. Min Range: -3.0968
Max Act: 2.9388. Min Act: -0.1700
Data Index: 289652 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0968. Min Range: -3.0968
Max Act: 2.9229. Min Act: -0.1700
Data Index: 121130 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0968. Min Range: -3.0968
Max Act: 2.9229. Min Act: -0.1700
Data Index: 704503 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0968. Min Range: -3.0968
Max Act: 2.9071. Min Act: -0.1700
Data Index: 798594 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0968. Min Range: -3.0968
Max Act: 2.9071. Min Act: -0.1700
Data Index: 989180 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0968. Min Range: -3.0968
Max Act: 2.8912. Min Act: -0.1700
Data Index: 153283 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0968. Min Range: -3.0968
Max Act: 2.8912. Min Act: -0.1700
Data Index: 811532 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0968. Min Range: -3.0968
Max Act: 2.8912. Min Act: -0.1700
Data Index: 520760 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0968. Min Range: -3.0968
Max Act: 2.8912. Min Act: -0.1700
Data Index: 982530 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0968. Min Range: -3.0968
Max Act: 2.8595. Min Act: -0.1700
Data Index: 362633 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0968. Min Range: -3.0968
Max Act: 2.8754. Min Act: -0.1700
Data Index: 1347614 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0968. Min Range: -3.0968
Max Act: 2.8754. Min Act: -0.1700
Data Index: 270402 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0968. Min Range: -3.0968
Max Act: 2.8754. Min Act: -0.1700
Data Index: 64418 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0968. Min Range: -3.0968
Max Act: 2.8595. Min Act: -0.1700
Data Index: 20442 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0968. Min Range: -3.0968
Max Act: 2.8595. Min Act: -0.1700
Data Index: 522121 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0968. Min Range: -3.0968
Max Act: 2.8595. Min Act: -0.1700
Data Index: 314900 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0968. Min Range: -3.0968
Max Act: 2.8595. Min Act: -0.1700
Data Index: 92359 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19