Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1382 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7109. Min Range: -2.7109
Max Act: 2.7109. Min Act: -0.1700
Data Index: 588933 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7109. Min Range: -2.7109
Max Act: 2.6788. Min Act: -0.1700
Data Index: 1393091 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7109. Min Range: -2.7109
Max Act: 2.6628. Min Act: -0.1700
Data Index: 663136 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7109. Min Range: -2.7109
Max Act: 2.6307. Min Act: -0.1700
Data Index: 854965 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7109. Min Range: -2.7109
Max Act: 2.6147. Min Act: -0.1700
Data Index: 1401633 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7109. Min Range: -2.7109
Max Act: 2.6468. Min Act: -0.1700
Data Index: 318895 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7109. Min Range: -2.7109
Max Act: 2.6307. Min Act: -0.1700
Data Index: 834946 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7109. Min Range: -2.7109
Max Act: 2.6307. Min Act: -0.1700
Data Index: 891901 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7109. Min Range: -2.7109
Max Act: 2.6147. Min Act: -0.1700
Data Index: 1339975 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7109. Min Range: -2.7109
Max Act: 2.6147. Min Act: -0.1700
Data Index: 161129 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7109. Min Range: -2.7109
Max Act: 2.6147. Min Act: -0.1700
Data Index: 828667 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7109. Min Range: -2.7109
Max Act: 2.5986. Min Act: -0.1700
Data Index: 706205 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7109. Min Range: -2.7109
Max Act: 2.6147. Min Act: -0.1700
Data Index: 1278027 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7109. Min Range: -2.7109
Max Act: 2.5986. Min Act: -0.1700
Data Index: 1501606 (Python Code)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7109. Min Range: -2.7109
Max Act: 2.5986. Min Act: -0.1700
Data Index: 1634487 (Python Code)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7109. Min Range: -2.7109
Max Act: 2.5986. Min Act: -0.1700
Data Index: 138171 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7109. Min Range: -2.7109
Max Act: 2.5986. Min Act: -0.1700
Data Index: 940563 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7109. Min Range: -2.7109
Max Act: 2.5986. Min Act: -0.1700
Data Index: 1305250 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7109. Min Range: -2.7109
Max Act: 2.5825. Min Act: -0.1700
Data Index: 648617 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7109. Min Range: -2.7109
Max Act: 2.5825. Min Act: -0.1700
Data Index: 825493 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19