Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2035 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.1668. Min Range: -5.1668
Max Act: 5.1668. Min Act: -0.1700
Data Index: 1284297 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1668. Min Range: -5.1668
Max Act: 4.9168. Min Act: -0.1700
Data Index: 674620 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1668. Min Range: -5.1668
Max Act: 4.6043. Min Act: -0.1700
Data Index: 1092889 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1668. Min Range: -5.1668
Max Act: 4.7605. Min Act: -0.1700
Data Index: 61059 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1668. Min Range: -5.1668
Max Act: 4.6668. Min Act: -0.1700
Data Index: 792049 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1668. Min Range: -5.1668
Max Act: 4.6355. Min Act: -0.1700
Data Index: 853301 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1668. Min Range: -5.1668
Max Act: 4.5418. Min Act: -0.1700
Data Index: 356996 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1668. Min Range: -5.1668
Max Act: 4.5418. Min Act: -0.1700
Data Index: 387010 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1668. Min Range: -5.1668
Max Act: 4.4792. Min Act: -0.1700
Data Index: 1146998 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1668. Min Range: -5.1668
Max Act: 4.5105. Min Act: -0.1700
Data Index: 18499 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1668. Min Range: -5.1668
Max Act: 4.4792. Min Act: -0.1700
Data Index: 527428 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1668. Min Range: -5.1668
Max Act: 4.4792. Min Act: -0.1700
Data Index: 1034125 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1668. Min Range: -5.1668
Max Act: 4.4480. Min Act: -0.1700
Data Index: 929159 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1668. Min Range: -5.1668
Max Act: 4.3542. Min Act: -0.1700
Data Index: 786340 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1668. Min Range: -5.1668
Max Act: 4.3542. Min Act: -0.1700
Data Index: 286527 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1668. Min Range: -5.1668
Max Act: 4.4480. Min Act: -0.1700
Data Index: 218570 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1668. Min Range: -5.1668
Max Act: 4.4480. Min Act: -0.1700
Data Index: 1252311 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1668. Min Range: -5.1668
Max Act: 4.4167. Min Act: -0.1700
Data Index: 999880 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1668. Min Range: -5.1668
Max Act: 4.3542. Min Act: -0.1700
Data Index: 383553 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1668. Min Range: -5.1668
Max Act: 4.3855. Min Act: -0.1700
Data Index: 382528 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19