Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1777 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0328. Min Range: -3.0328
Max Act: 3.0328. Min Act: -0.1700
Data Index: 1176775 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0328. Min Range: -3.0328
Max Act: 2.9854. Min Act: -0.1700
Data Index: 38641 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0328. Min Range: -3.0328
Max Act: 2.9854. Min Act: -0.1700
Data Index: 506672 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0328. Min Range: -3.0328
Max Act: 2.9379. Min Act: -0.1700
Data Index: 1502833 (Python Code)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0328. Min Range: -3.0328
Max Act: 2.9695. Min Act: -0.1700
Data Index: 240059 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0328. Min Range: -3.0328
Max Act: 2.9695. Min Act: -0.1700
Data Index: 1394341 (Python Code)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0328. Min Range: -3.0328
Max Act: 2.9220. Min Act: -0.1700
Data Index: 1548110 (Python Code)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0328. Min Range: -3.0328
Max Act: 2.9379. Min Act: -0.1700
Data Index: 391565 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0328. Min Range: -3.0328
Max Act: 2.9379. Min Act: -0.1700
Data Index: 1338124 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0328. Min Range: -3.0328
Max Act: 2.9062. Min Act: -0.1700
Data Index: 1496109 (Python Code)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0328. Min Range: -3.0328
Max Act: 2.8744. Min Act: -0.1700
Data Index: 984275 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0328. Min Range: -3.0328
Max Act: 2.8903. Min Act: -0.1700
Data Index: 999020 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0328. Min Range: -3.0328
Max Act: 2.9062. Min Act: -0.1700
Data Index: 903196 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0328. Min Range: -3.0328
Max Act: 2.8744. Min Act: -0.1700
Data Index: 1626860 (Python Code)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0328. Min Range: -3.0328
Max Act: 2.8903. Min Act: -0.1700
Data Index: 39770 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0328. Min Range: -3.0328
Max Act: 2.8903. Min Act: -0.1700
Data Index: 1336783 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0328. Min Range: -3.0328
Max Act: 2.9220. Min Act: -0.1700
Data Index: 1009457 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0328. Min Range: -3.0328
Max Act: 2.8744. Min Act: -0.1700
Data Index: 962933 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0328. Min Range: -3.0328
Max Act: 2.8903. Min Act: -0.1700
Data Index: 1133548 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0328. Min Range: -3.0328
Max Act: 2.8586. Min Act: -0.1700
Data Index: 111111 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19