Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1101 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9786. Min Range: -4.9786
Max Act: 4.9786. Min Act: -0.1700
Data Index: 909390 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9786. Min Range: -4.9786
Max Act: 4.9786. Min Act: -0.1700
Data Index: 166552 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9786. Min Range: -4.9786
Max Act: 4.9786. Min Act: -0.1700
Data Index: 1348159 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9786. Min Range: -4.9786
Max Act: 4.9786. Min Act: -0.1700
Data Index: 628174 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9786. Min Range: -4.9786
Max Act: 4.9786. Min Act: -0.1700
Data Index: 41466 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9786. Min Range: -4.9786
Max Act: 4.9786. Min Act: -0.1700
Data Index: 562309 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9786. Min Range: -4.9786
Max Act: 4.9473. Min Act: -0.1700
Data Index: 539802 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9786. Min Range: -4.9786
Max Act: 4.9473. Min Act: -0.1700
Data Index: 998291 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9786. Min Range: -4.9786
Max Act: 4.8848. Min Act: -0.1700
Data Index: 502981 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9786. Min Range: -4.9786
Max Act: 4.9161. Min Act: -0.1700
Data Index: 377484 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9786. Min Range: -4.9786
Max Act: 4.8536. Min Act: -0.1700
Data Index: 351675 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9786. Min Range: -4.9786
Max Act: 4.8848. Min Act: -0.1700
Data Index: 37254 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9786. Min Range: -4.9786
Max Act: 4.8848. Min Act: -0.1700
Data Index: 38499 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9786. Min Range: -4.9786
Max Act: 4.9161. Min Act: -0.1700
Data Index: 641602 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9786. Min Range: -4.9786
Max Act: 4.8536. Min Act: -0.1700
Data Index: 1087666 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9786. Min Range: -4.9786
Max Act: 4.8536. Min Act: -0.1700
Data Index: 588628 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9786. Min Range: -4.9786
Max Act: 4.8536. Min Act: -0.1700
Data Index: 967163 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9786. Min Range: -4.9786
Max Act: 4.8536. Min Act: -0.1700
Data Index: 288560 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9786. Min Range: -4.9786
Max Act: 4.8536. Min Act: -0.1700
Data Index: 196880 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9786. Min Range: -4.9786
Max Act: 4.8223. Min Act: -0.1699
Data Index: 736988 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #19