Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 632 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.0293. Min Range: -6.0293
Max Act: 6.0293. Min Act: -0.1700
Data Index: 1286301 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0293. Min Range: -6.0293
Max Act: 5.9356. Min Act: -0.1699
Data Index: 841845 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0293. Min Range: -6.0293
Max Act: 5.9043. Min Act: -0.1700
Data Index: 1216164 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0293. Min Range: -6.0293
Max Act: 5.9043. Min Act: -0.1700
Data Index: 754751 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0293. Min Range: -6.0293
Max Act: 5.9043. Min Act: -0.1700
Data Index: 779145 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0293. Min Range: -6.0293
Max Act: 5.8418. Min Act: -0.1700
Data Index: 906882 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0293. Min Range: -6.0293
Max Act: 5.9043. Min Act: -0.1700
Data Index: 222403 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0293. Min Range: -6.0293
Max Act: 5.8106. Min Act: -0.1700
Data Index: 10439 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0293. Min Range: -6.0293
Max Act: 5.8418. Min Act: -0.1700
Data Index: 1226962 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0293. Min Range: -6.0293
Max Act: 5.7793. Min Act: -0.1700
Data Index: 455339 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0293. Min Range: -6.0293
Max Act: 5.8106. Min Act: -0.1700
Data Index: 144197 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0293. Min Range: -6.0293
Max Act: 5.8106. Min Act: -0.1700
Data Index: 46811 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0293. Min Range: -6.0293
Max Act: 5.7481. Min Act: -0.1700
Data Index: 1241029 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0293. Min Range: -6.0293
Max Act: 5.7793. Min Act: -0.1700
Data Index: 1028988 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0293. Min Range: -6.0293
Max Act: 5.7481. Min Act: -0.1700
Data Index: 1300890 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0293. Min Range: -6.0293
Max Act: 5.7481. Min Act: -0.1700
Data Index: 169536 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0293. Min Range: -6.0293
Max Act: 5.7481. Min Act: -0.1700
Data Index: 609716 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0293. Min Range: -6.0293
Max Act: 5.7481. Min Act: -0.1700
Data Index: 557326 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0293. Min Range: -6.0293
Max Act: 5.7481. Min Act: -0.1700
Data Index: 1144680 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0293. Min Range: -6.0293
Max Act: 5.7168. Min Act: -0.1700
Data Index: 131733 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19