Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1827 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8542. Min Range: -2.8542
Max Act: 2.8542. Min Act: -0.1700
Data Index: 807392 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8542. Min Range: -2.8542
Max Act: 2.8383. Min Act: -0.1700
Data Index: 711554 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8542. Min Range: -2.8542
Max Act: 2.7268. Min Act: -0.1700
Data Index: 1028559 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8542. Min Range: -2.8542
Max Act: 2.7268. Min Act: -0.1700
Data Index: 103790 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8542. Min Range: -2.8542
Max Act: 2.7268. Min Act: -0.1700
Data Index: 29644 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8542. Min Range: -2.8542
Max Act: 2.7108. Min Act: -0.1700
Data Index: 673856 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8542. Min Range: -2.8542
Max Act: 2.7268. Min Act: -0.1700
Data Index: 1236859 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8542. Min Range: -2.8542
Max Act: 2.6948. Min Act: -0.1700
Data Index: 622784 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8542. Min Range: -2.8542
Max Act: 2.6948. Min Act: -0.1700
Data Index: 149231 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8542. Min Range: -2.8542
Max Act: 2.6948. Min Act: -0.1700
Data Index: 192336 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8542. Min Range: -2.8542
Max Act: 2.6948. Min Act: -0.1700
Data Index: 1103036 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8542. Min Range: -2.8542
Max Act: 2.6948. Min Act: -0.1700
Data Index: 1157083 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8542. Min Range: -2.8542
Max Act: 2.6627. Min Act: -0.1700
Data Index: 1041125 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8542. Min Range: -2.8542
Max Act: 2.6788. Min Act: -0.1700
Data Index: 996014 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8542. Min Range: -2.8542
Max Act: 2.6788. Min Act: -0.1700
Data Index: 658933 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8542. Min Range: -2.8542
Max Act: 2.6467. Min Act: -0.1700
Data Index: 345145 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8542. Min Range: -2.8542
Max Act: 2.6627. Min Act: -0.1700
Data Index: 1200830 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8542. Min Range: -2.8542
Max Act: 2.6627. Min Act: -0.1700
Data Index: 277775 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8542. Min Range: -2.8542
Max Act: 2.6627. Min Act: -0.1700
Data Index: 57928 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8542. Min Range: -2.8542
Max Act: 2.6306. Min Act: -0.1700
Data Index: 962541 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19