Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 31 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6886. Min Range: -2.6886
Max Act: 2.6886. Min Act: -0.1700
Data Index: 1150853 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6886. Min Range: -2.6886
Max Act: 2.6726. Min Act: -0.1700
Data Index: 1480258 (Python Code)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6886. Min Range: -2.6886
Max Act: 2.6565. Min Act: -0.1700
Data Index: 996965 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6886. Min Range: -2.6886
Max Act: 2.6565. Min Act: -0.1700
Data Index: 1379268 (Python Code)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6886. Min Range: -2.6886
Max Act: 2.6565. Min Act: -0.1700
Data Index: 1526335 (Python Code)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6886. Min Range: -2.6886
Max Act: 2.6565. Min Act: -0.1700
Data Index: 1442692 (Python Code)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6886. Min Range: -2.6886
Max Act: 2.6405. Min Act: -0.1700
Data Index: 1606038 (Python Code)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6886. Min Range: -2.6886
Max Act: 2.6405. Min Act: -0.1700
Data Index: 1488479 (Python Code)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6886. Min Range: -2.6886
Max Act: 2.6405. Min Act: -0.1700
Data Index: 1560734 (Python Code)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6886. Min Range: -2.6886
Max Act: 2.6405. Min Act: -0.1700
Data Index: 519373 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6886. Min Range: -2.6886
Max Act: 2.6244. Min Act: -0.1700
Data Index: 1399108 (Python Code)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6886. Min Range: -2.6886
Max Act: 2.6244. Min Act: -0.1700
Data Index: 783207 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6886. Min Range: -2.6886
Max Act: 2.6244. Min Act: -0.1700
Data Index: 876826 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6886. Min Range: -2.6886
Max Act: 2.6083. Min Act: -0.1700
Data Index: 358330 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6886. Min Range: -2.6886
Max Act: 2.6083. Min Act: -0.1700
Data Index: 1371764 (Python Code)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6886. Min Range: -2.6886
Max Act: 2.5923. Min Act: -0.1700
Data Index: 1505111 (Python Code)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6886. Min Range: -2.6886
Max Act: 2.5923. Min Act: -0.1700
Data Index: 1519658 (Python Code)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6886. Min Range: -2.6886
Max Act: 2.5923. Min Act: -0.1700
Data Index: 482825 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6886. Min Range: -2.6886
Max Act: 2.5923. Min Act: -0.1700
Data Index: 1434546 (Python Code)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6886. Min Range: -2.6886
Max Act: 2.5923. Min Act: -0.1700
Data Index: 108642 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19