Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1683 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 1.5054. Min Range: -1.5054
Max Act: 1.5054. Min Act: -0.0001
Data Index: 169700 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5054. Min Range: -1.5054
Max Act: 1.3542. Min Act: -0.0001
Data Index: 80384 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5054. Min Range: -1.5054
Max Act: 1.3175. Min Act: -0.0001
Data Index: 328449 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5054. Min Range: -1.5054
Max Act: 1.3166. Min Act: -0.0001
Data Index: 947830 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5054. Min Range: -1.5054
Max Act: 1.3846. Min Act: -0.0001
Data Index: 1147614 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5054. Min Range: -1.5054
Max Act: 1.2623. Min Act: -0.0001
Data Index: 922312 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5054. Min Range: -1.5054
Max Act: 1.3653. Min Act: -0.0001
Data Index: 895906 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5054. Min Range: -1.5054
Max Act: 1.3526. Min Act: -0.0001
Data Index: 482721 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5054. Min Range: -1.5054
Max Act: 1.3545. Min Act: -0.0001
Data Index: 1228355 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5054. Min Range: -1.5054
Max Act: 1.2919. Min Act: -0.0001
Data Index: 1248295 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5054. Min Range: -1.5054
Max Act: 1.2403. Min Act: -0.0001
Data Index: 736245 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5054. Min Range: -1.5054
Max Act: 1.2859. Min Act: -0.0001
Data Index: 248235 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5054. Min Range: -1.5054
Max Act: 1.4094. Min Act: -0.0001
Data Index: 1245192 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5054. Min Range: -1.5054
Max Act: 1.2459. Min Act: -0.0001
Data Index: 955630 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5054. Min Range: -1.5054
Max Act: 1.0795. Min Act: -0.0001
Data Index: 669750 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5054. Min Range: -1.5054
Max Act: 1.3731. Min Act: -0.0001
Data Index: 510881 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5054. Min Range: -1.5054
Max Act: 1.1729. Min Act: -0.0001
Data Index: 643246 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5054. Min Range: -1.5054
Max Act: 1.2579. Min Act: -0.0001
Data Index: 663789 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5054. Min Range: -1.5054
Max Act: 1.1339. Min Act: -0.0001
Data Index: 396949 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5054. Min Range: -1.5054
Max Act: 1.0666. Min Act: -0.0001
Data Index: 255535 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19