Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1407 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.0958. Min Range: -3.0958
Max Act: 3.0958. Min Act: -0.1700
Data Index: 575377 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0958. Min Range: -3.0958
Max Act: 3.0327. Min Act: -0.1700
Data Index: 485756 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0958. Min Range: -3.0958
Max Act: 3.0169. Min Act: -0.1700
Data Index: 1298028 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0958. Min Range: -3.0958
Max Act: 3.0011. Min Act: -0.1700
Data Index: 754719 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0958. Min Range: -3.0958
Max Act: 2.9853. Min Act: -0.1700
Data Index: 380905 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0958. Min Range: -3.0958
Max Act: 2.9695. Min Act: -0.1700
Data Index: 817470 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0958. Min Range: -3.0958
Max Act: 2.9695. Min Act: -0.1700
Data Index: 1310570 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0958. Min Range: -3.0958
Max Act: 2.9695. Min Act: -0.1700
Data Index: 989471 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0958. Min Range: -3.0958
Max Act: 2.9695. Min Act: -0.1700
Data Index: 677667 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0958. Min Range: -3.0958
Max Act: 2.9853. Min Act: -0.1700
Data Index: 1140990 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0958. Min Range: -3.0958
Max Act: 2.9536. Min Act: -0.1700
Data Index: 738293 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0958. Min Range: -3.0958
Max Act: 2.9695. Min Act: -0.1700
Data Index: 177031 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0958. Min Range: -3.0958
Max Act: 2.9536. Min Act: -0.1700
Data Index: 505667 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0958. Min Range: -3.0958
Max Act: 2.9695. Min Act: -0.1700
Data Index: 1271405 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0958. Min Range: -3.0958
Max Act: 2.9695. Min Act: -0.1700
Data Index: 1101977 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0958. Min Range: -3.0958
Max Act: 2.9378. Min Act: -0.1700
Data Index: 132746 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0958. Min Range: -3.0958
Max Act: 2.9378. Min Act: -0.1700
Data Index: 455744 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0958. Min Range: -3.0958
Max Act: 2.9695. Min Act: -0.1700
Data Index: 1285797 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0958. Min Range: -3.0958
Max Act: 2.9695. Min Act: -0.1700
Data Index: 1003688 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0958. Min Range: -3.0958
Max Act: 2.9378. Min Act: -0.1700
Data Index: 350903 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19