Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 530 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.1276. Min Range: -4.1276
Max Act: 4.1276. Min Act: -0.1700
Data Index: 168748 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1276. Min Range: -4.1276
Max Act: 3.9713. Min Act: -0.1700
Data Index: 577974 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1276. Min Range: -4.1276
Max Act: 3.9400. Min Act: -0.1700
Data Index: 950414 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1276. Min Range: -4.1276
Max Act: 3.9087. Min Act: -0.1700
Data Index: 487315 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1276. Min Range: -4.1276
Max Act: 3.9087. Min Act: -0.1700
Data Index: 508306 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1276. Min Range: -4.1276
Max Act: 3.8618. Min Act: -0.1700
Data Index: 1066147 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1276. Min Range: -4.1276
Max Act: 3.8775. Min Act: -0.1700
Data Index: 874066 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1276. Min Range: -4.1276
Max Act: 3.8305. Min Act: -0.1700
Data Index: 1657012 (Python Code)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1276. Min Range: -4.1276
Max Act: 3.8462. Min Act: -0.1700
Data Index: 932197 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1276. Min Range: -4.1276
Max Act: 3.8305. Min Act: -0.1700
Data Index: 1171060 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1276. Min Range: -4.1276
Max Act: 3.8305. Min Act: -0.1700
Data Index: 471824 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1276. Min Range: -4.1276
Max Act: 3.8775. Min Act: -0.1700
Data Index: 1550753 (Python Code)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1276. Min Range: -4.1276
Max Act: 3.8305. Min Act: -0.1700
Data Index: 103751 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1276. Min Range: -4.1276
Max Act: 3.8149. Min Act: -0.1700
Data Index: 706719 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1276. Min Range: -4.1276
Max Act: 3.8305. Min Act: -0.1700
Data Index: 300289 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1276. Min Range: -4.1276
Max Act: 3.7993. Min Act: -0.1700
Data Index: 350494 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1276. Min Range: -4.1276
Max Act: 3.7836. Min Act: -0.1700
Data Index: 454880 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1276. Min Range: -4.1276
Max Act: 3.7680. Min Act: -0.1700
Data Index: 729738 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1276. Min Range: -4.1276
Max Act: 3.7836. Min Act: -0.1700
Data Index: 1351918 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1276. Min Range: -4.1276
Max Act: 3.7836. Min Act: -0.1700
Data Index: 698322 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19