Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1952 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7370. Min Range: -2.7370
Max Act: 2.7370. Min Act: -0.1700
Data Index: 707176 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7370. Min Range: -2.7370
Max Act: 2.7051. Min Act: -0.1700
Data Index: 856203 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7370. Min Range: -2.7370
Max Act: 2.6890. Min Act: -0.1700
Data Index: 238076 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7370. Min Range: -2.7370
Max Act: 2.6570. Min Act: -0.1700
Data Index: 69796 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7370. Min Range: -2.7370
Max Act: 2.6410. Min Act: -0.1700
Data Index: 259737 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7370. Min Range: -2.7370
Max Act: 2.6410. Min Act: -0.1700
Data Index: 1103979 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7370. Min Range: -2.7370
Max Act: 2.5927. Min Act: -0.1700
Data Index: 1544855 (Python Code)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7370. Min Range: -2.7370
Max Act: 2.5605. Min Act: -0.1700
Data Index: 970137 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7370. Min Range: -2.7370
Max Act: 2.5605. Min Act: -0.1700
Data Index: 1138890 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7370. Min Range: -2.7370
Max Act: 2.5605. Min Act: -0.1700
Data Index: 1266723 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7370. Min Range: -2.7370
Max Act: 2.5605. Min Act: -0.1700
Data Index: 820283 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7370. Min Range: -2.7370
Max Act: 2.5444. Min Act: -0.1700
Data Index: 320379 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7370. Min Range: -2.7370
Max Act: 2.5444. Min Act: -0.1700
Data Index: 1539736 (Python Code)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7370. Min Range: -2.7370
Max Act: 2.5282. Min Act: -0.1700
Data Index: 852970 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7370. Min Range: -2.7370
Max Act: 2.5444. Min Act: -0.1700
Data Index: 1158429 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7370. Min Range: -2.7370
Max Act: 2.5120. Min Act: -0.1700
Data Index: 648753 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7370. Min Range: -2.7370
Max Act: 2.5120. Min Act: -0.1700
Data Index: 1148961 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7370. Min Range: -2.7370
Max Act: 2.5282. Min Act: -0.1700
Data Index: 398887 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7370. Min Range: -2.7370
Max Act: 2.4958. Min Act: -0.1700
Data Index: 1015078 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7370. Min Range: -2.7370
Max Act: 2.4958. Min Act: -0.1700
Data Index: 268800 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19