Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 233 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.1356. Min Range: -5.1356
Max Act: 5.1356. Min Act: -0.1700
Data Index: 387128 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1356. Min Range: -5.1356
Max Act: 4.8543. Min Act: -0.1700
Data Index: 448888 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1356. Min Range: -5.1356
Max Act: 4.8543. Min Act: -0.1700
Data Index: 318205 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1356. Min Range: -5.1356
Max Act: 4.7606. Min Act: -0.1700
Data Index: 109559 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1356. Min Range: -5.1356
Max Act: 4.7918. Min Act: -0.1700
Data Index: 1247934 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1356. Min Range: -5.1356
Max Act: 4.7918. Min Act: -0.1700
Data Index: 574808 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1356. Min Range: -5.1356
Max Act: 4.7606. Min Act: -0.1700
Data Index: 714300 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1356. Min Range: -5.1356
Max Act: 4.6981. Min Act: -0.1700
Data Index: 164009 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1356. Min Range: -5.1356
Max Act: 4.6981. Min Act: -0.1700
Data Index: 309860 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1356. Min Range: -5.1356
Max Act: 4.6356. Min Act: -0.1700
Data Index: 752261 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1356. Min Range: -5.1356
Max Act: 4.6981. Min Act: -0.1700
Data Index: 52627 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1356. Min Range: -5.1356
Max Act: 4.6668. Min Act: -0.1700
Data Index: 1023549 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1356. Min Range: -5.1356
Max Act: 4.6356. Min Act: -0.1700
Data Index: 117476 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1356. Min Range: -5.1356
Max Act: 4.6356. Min Act: -0.1700
Data Index: 217594 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1356. Min Range: -5.1356
Max Act: 4.6668. Min Act: -0.1700
Data Index: 433157 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1356. Min Range: -5.1356
Max Act: 4.6043. Min Act: -0.1700
Data Index: 392851 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1356. Min Range: -5.1356
Max Act: 4.5731. Min Act: -0.1700
Data Index: 200115 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1356. Min Range: -5.1356
Max Act: 4.6043. Min Act: -0.1700
Data Index: 184319 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1356. Min Range: -5.1356
Max Act: 4.6356. Min Act: -0.1700
Data Index: 987716 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1356. Min Range: -5.1356
Max Act: 4.5731. Min Act: -0.1700
Data Index: 870580 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19