Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 159 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3957. Min Range: -4.3957
Max Act: 4.3957. Min Act: -0.1700
Data Index: 1175822 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3957. Min Range: -4.3957
Max Act: 4.1769. Min Act: -0.1700
Data Index: 1003035 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3957. Min Range: -4.3957
Max Act: 4.1457. Min Act: -0.1700
Data Index: 78113 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3957. Min Range: -4.3957
Max Act: 4.0831. Min Act: -0.1700
Data Index: 1255674 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3957. Min Range: -4.3957
Max Act: 4.0831. Min Act: -0.1700
Data Index: 1081976 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3957. Min Range: -4.3957
Max Act: 4.0519. Min Act: -0.1700
Data Index: 913350 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3957. Min Range: -4.3957
Max Act: 4.0519. Min Act: -0.1700
Data Index: 296704 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3957. Min Range: -4.3957
Max Act: 4.0519. Min Act: -0.1700
Data Index: 852334 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3957. Min Range: -4.3957
Max Act: 4.0519. Min Act: -0.1700
Data Index: 1342735 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3957. Min Range: -4.3957
Max Act: 4.0519. Min Act: -0.1700
Data Index: 267250 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3957. Min Range: -4.3957
Max Act: 4.0831. Min Act: -0.1700
Data Index: 139304 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3957. Min Range: -4.3957
Max Act: 4.0206. Min Act: -0.1700
Data Index: 1127358 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3957. Min Range: -4.3957
Max Act: 4.0206. Min Act: -0.1700
Data Index: 1170428 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3957. Min Range: -4.3957
Max Act: 4.0519. Min Act: -0.1700
Data Index: 718138 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3957. Min Range: -4.3957
Max Act: 4.0206. Min Act: -0.1700
Data Index: 1179847 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3957. Min Range: -4.3957
Max Act: 3.9893. Min Act: -0.1700
Data Index: 885873 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3957. Min Range: -4.3957
Max Act: 3.9893. Min Act: -0.1700
Data Index: 1275276 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3957. Min Range: -4.3957
Max Act: 3.9893. Min Act: -0.1700
Data Index: 825391 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3957. Min Range: -4.3957
Max Act: 4.0206. Min Act: -0.1700
Data Index: 40774 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3957. Min Range: -4.3957
Max Act: 3.9893. Min Act: -0.1700
Data Index: 849453 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19