Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 961 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5699. Min Range: -2.5699
Max Act: 2.5699. Min Act: -0.1700
Data Index: 260026 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5699. Min Range: -2.5699
Max Act: 2.5699. Min Act: -0.1700
Data Index: 283846 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5699. Min Range: -2.5699
Max Act: 2.5537. Min Act: -0.1700
Data Index: 1061122 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5699. Min Range: -2.5699
Max Act: 2.5376. Min Act: -0.1700
Data Index: 1039532 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5699. Min Range: -2.5699
Max Act: 2.5376. Min Act: -0.1700
Data Index: 212719 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5699. Min Range: -2.5699
Max Act: 2.5052. Min Act: -0.1700
Data Index: 1160791 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5699. Min Range: -2.5699
Max Act: 2.4890. Min Act: -0.1700
Data Index: 1118713 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5699. Min Range: -2.5699
Max Act: 2.4890. Min Act: -0.1700
Data Index: 800775 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5699. Min Range: -2.5699
Max Act: 2.4728. Min Act: -0.1700
Data Index: 168415 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5699. Min Range: -2.5699
Max Act: 2.5052. Min Act: -0.1700
Data Index: 820106 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5699. Min Range: -2.5699
Max Act: 2.4890. Min Act: -0.1700
Data Index: 1163224 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5699. Min Range: -2.5699
Max Act: 2.4728. Min Act: -0.1700
Data Index: 981782 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5699. Min Range: -2.5699
Max Act: 2.4728. Min Act: -0.1700
Data Index: 181965 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5699. Min Range: -2.5699
Max Act: 2.4890. Min Act: -0.1700
Data Index: 12178 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5699. Min Range: -2.5699
Max Act: 2.4566. Min Act: -0.1700
Data Index: 1116100 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5699. Min Range: -2.5699
Max Act: 2.4566. Min Act: -0.1700
Data Index: 952488 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5699. Min Range: -2.5699
Max Act: 2.4566. Min Act: -0.1700
Data Index: 781948 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5699. Min Range: -2.5699
Max Act: 2.4566. Min Act: -0.1700
Data Index: 152637 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5699. Min Range: -2.5699
Max Act: 2.4566. Min Act: -0.1700
Data Index: 876031 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5699. Min Range: -2.5699
Max Act: 2.4403. Min Act: -0.1700
Data Index: 785716 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19