Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 154 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.3199. Min Range: -6.3199
Max Act: 6.3199. Min Act: -0.1700
Data Index: 517421 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3199. Min Range: -6.3199
Max Act: 6.3043. Min Act: -0.1700
Data Index: 964689 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3199. Min Range: -6.3199
Max Act: 6.1480. Min Act: -0.1700
Data Index: 253173 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3199. Min Range: -6.3199
Max Act: 6.0699. Min Act: -0.1700
Data Index: 198024 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3199. Min Range: -6.3199
Max Act: 6.0230. Min Act: -0.1700
Data Index: 321380 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3199. Min Range: -6.3199
Max Act: 6.0543. Min Act: -0.1700
Data Index: 868260 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3199. Min Range: -6.3199
Max Act: 5.9761. Min Act: -0.1700
Data Index: 465467 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3199. Min Range: -6.3199
Max Act: 5.9605. Min Act: -0.1700
Data Index: 468906 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3199. Min Range: -6.3199
Max Act: 6.0386. Min Act: -0.1700
Data Index: 1358395 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3199. Min Range: -6.3199
Max Act: 5.9136. Min Act: -0.1700
Data Index: 1317519 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3199. Min Range: -6.3199
Max Act: 5.8824. Min Act: -0.1700
Data Index: 483819 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3199. Min Range: -6.3199
Max Act: 5.8980. Min Act: -0.1700
Data Index: 787134 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3199. Min Range: -6.3199
Max Act: 5.8511. Min Act: -0.1700
Data Index: 221765 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3199. Min Range: -6.3199
Max Act: 5.8824. Min Act: -0.1700
Data Index: 162580 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3199. Min Range: -6.3199
Max Act: 5.9761. Min Act: -0.1700
Data Index: 135794 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3199. Min Range: -6.3199
Max Act: 5.8824. Min Act: -0.1700
Data Index: 883319 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3199. Min Range: -6.3199
Max Act: 5.8355. Min Act: -0.1700
Data Index: 33767 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3199. Min Range: -6.3199
Max Act: 5.8355. Min Act: -0.1700
Data Index: 886115 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3199. Min Range: -6.3199
Max Act: 5.8511. Min Act: -0.1700
Data Index: 714304 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3199. Min Range: -6.3199
Max Act: 5.7886. Min Act: -0.1700
Data Index: 155746 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19