Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1804 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.1827. Min Range: -3.1827
Max Act: 3.1827. Min Act: -0.1700
Data Index: 1103860 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1827. Min Range: -3.1827
Max Act: 3.1670. Min Act: -0.1700
Data Index: 184439 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1827. Min Range: -3.1827
Max Act: 3.1670. Min Act: -0.1700
Data Index: 1154675 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1827. Min Range: -3.1827
Max Act: 3.1512. Min Act: -0.1700
Data Index: 314666 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1827. Min Range: -3.1827
Max Act: 3.1670. Min Act: -0.1700
Data Index: 741292 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1827. Min Range: -3.1827
Max Act: 3.1512. Min Act: -0.1700
Data Index: 532326 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1827. Min Range: -3.1827
Max Act: 3.1512. Min Act: -0.1700
Data Index: 55911 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1827. Min Range: -3.1827
Max Act: 3.1355. Min Act: -0.1700
Data Index: 991459 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1827. Min Range: -3.1827
Max Act: 3.1355. Min Act: -0.1700
Data Index: 1189861 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1827. Min Range: -3.1827
Max Act: 3.1197. Min Act: -0.1700
Data Index: 889079 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1827. Min Range: -3.1827
Max Act: 3.1197. Min Act: -0.1700
Data Index: 60266 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1827. Min Range: -3.1827
Max Act: 3.1197. Min Act: -0.1700
Data Index: 955921 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1827. Min Range: -3.1827
Max Act: 3.1197. Min Act: -0.1700
Data Index: 119821 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1827. Min Range: -3.1827
Max Act: 3.1197. Min Act: -0.1700
Data Index: 80878 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1827. Min Range: -3.1827
Max Act: 3.1039. Min Act: -0.1700
Data Index: 21250 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1827. Min Range: -3.1827
Max Act: 3.1197. Min Act: -0.1700
Data Index: 210410 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1827. Min Range: -3.1827
Max Act: 3.1039. Min Act: -0.1700
Data Index: 1058375 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1827. Min Range: -3.1827
Max Act: 3.1197. Min Act: -0.1700
Data Index: 141872 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1827. Min Range: -3.1827
Max Act: 3.0724. Min Act: -0.1700
Data Index: 1149743 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1827. Min Range: -3.1827
Max Act: 3.0882. Min Act: -0.1700
Data Index: 672536 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19