Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 207 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.9417. Min Range: -4.9417
Max Act: 4.9105. Min Act: -0.1700
Data Index: 344333 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9417. Min Range: -4.9417
Max Act: 4.9105. Min Act: -0.1700
Data Index: 501729 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9417. Min Range: -4.9417
Max Act: 4.9417. Min Act: -0.1700
Data Index: 1100571 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9417. Min Range: -4.9417
Max Act: 4.8792. Min Act: -0.1700
Data Index: 83284 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9417. Min Range: -4.9417
Max Act: 4.8792. Min Act: -0.1700
Data Index: 841928 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9417. Min Range: -4.9417
Max Act: 4.9417. Min Act: -0.1700
Data Index: 636399 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9417. Min Range: -4.9417
Max Act: 4.9105. Min Act: -0.1700
Data Index: 72945 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9417. Min Range: -4.9417
Max Act: 4.8792. Min Act: -0.1700
Data Index: 273993 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9417. Min Range: -4.9417
Max Act: 4.8792. Min Act: -0.1700
Data Index: 746680 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9417. Min Range: -4.9417
Max Act: 4.8480. Min Act: -0.1700
Data Index: 644529 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9417. Min Range: -4.9417
Max Act: 4.9417. Min Act: -0.1700
Data Index: 298017 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9417. Min Range: -4.9417
Max Act: 4.9105. Min Act: -0.1700
Data Index: 351498 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9417. Min Range: -4.9417
Max Act: 4.9417. Min Act: -0.1700
Data Index: 1351422 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9417. Min Range: -4.9417
Max Act: 4.9105. Min Act: -0.1700
Data Index: 741072 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9417. Min Range: -4.9417
Max Act: 4.8792. Min Act: -0.1700
Data Index: 1270691 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9417. Min Range: -4.9417
Max Act: 4.8480. Min Act: -0.1700
Data Index: 1016518 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9417. Min Range: -4.9417
Max Act: 4.8480. Min Act: -0.1700
Data Index: 760863 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9417. Min Range: -4.9417
Max Act: 4.8792. Min Act: -0.1700
Data Index: 456391 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9417. Min Range: -4.9417
Max Act: 4.8167. Min Act: -0.1700
Data Index: 657615 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9417. Min Range: -4.9417
Max Act: 4.8792. Min Act: -0.1700
Data Index: 225304 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19