Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1123 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3758. Min Range: -4.3758
Max Act: 4.3133. Min Act: -0.1700
Data Index: 1294592 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3758. Min Range: -4.3758
Max Act: 4.3758. Min Act: -0.1700
Data Index: 184365 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3758. Min Range: -4.3758
Max Act: 4.2821. Min Act: -0.1700
Data Index: 993115 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3758. Min Range: -4.3758
Max Act: 4.2195. Min Act: -0.1700
Data Index: 1100379 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3758. Min Range: -4.3758
Max Act: 4.2508. Min Act: -0.1700
Data Index: 395943 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3758. Min Range: -4.3758
Max Act: 4.2195. Min Act: -0.1700
Data Index: 981385 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3758. Min Range: -4.3758
Max Act: 4.2508. Min Act: -0.1700
Data Index: 333593 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3758. Min Range: -4.3758
Max Act: 4.2195. Min Act: -0.1700
Data Index: 589290 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3758. Min Range: -4.3758
Max Act: 4.2508. Min Act: -0.1700
Data Index: 1178123 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3758. Min Range: -4.3758
Max Act: 4.1883. Min Act: -0.1700
Data Index: 1296548 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3758. Min Range: -4.3758
Max Act: 4.1570. Min Act: -0.1700
Data Index: 560970 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3758. Min Range: -4.3758
Max Act: 4.1883. Min Act: -0.1700
Data Index: 429263 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3758. Min Range: -4.3758
Max Act: 4.1883. Min Act: -0.1700
Data Index: 705938 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3758. Min Range: -4.3758
Max Act: 4.1883. Min Act: -0.1700
Data Index: 725905 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3758. Min Range: -4.3758
Max Act: 4.2195. Min Act: -0.1700
Data Index: 124887 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3758. Min Range: -4.3758
Max Act: 4.1570. Min Act: -0.1700
Data Index: 277536 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3758. Min Range: -4.3758
Max Act: 4.1883. Min Act: -0.1700
Data Index: 771812 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3758. Min Range: -4.3758
Max Act: 4.1883. Min Act: -0.1700
Data Index: 268668 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3758. Min Range: -4.3758
Max Act: 4.1570. Min Act: -0.1700
Data Index: 776165 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3758. Min Range: -4.3758
Max Act: 4.1258. Min Act: -0.1700
Data Index: 783932 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19