Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2804 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.2904. Min Range: -2.2904
Max Act: 2.2904. Min Act: -0.0001
Data Index: 488242 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2904. Min Range: -2.2904
Max Act: 2.1739. Min Act: -0.0001
Data Index: 986190 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2904. Min Range: -2.2904
Max Act: 2.2582. Min Act: -0.0001
Data Index: 867410 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2904. Min Range: -2.2904
Max Act: 2.0184. Min Act: -0.0001
Data Index: 1098286 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2904. Min Range: -2.2904
Max Act: 2.1261. Min Act: -0.0001
Data Index: 1137348 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2904. Min Range: -2.2904
Max Act: 2.0009. Min Act: -0.0001
Data Index: 786943 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2904. Min Range: -2.2904
Max Act: 2.0937. Min Act: -0.0001
Data Index: 1338053 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2904. Min Range: -2.2904
Max Act: 1.9560. Min Act: -0.0001
Data Index: 1441025 (Python Code)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2904. Min Range: -2.2904
Max Act: 2.1489. Min Act: -0.0001
Data Index: 1092050 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2904. Min Range: -2.2904
Max Act: 1.9945. Min Act: -0.0001
Data Index: 654421 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2904. Min Range: -2.2904
Max Act: 1.9751. Min Act: -0.0001
Data Index: 568734 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2904. Min Range: -2.2904
Max Act: 1.8893. Min Act: -0.0001
Data Index: 1458175 (Python Code)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2904. Min Range: -2.2904
Max Act: 1.8467. Min Act: -0.0001
Data Index: 1544615 (Python Code)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2904. Min Range: -2.2904
Max Act: 1.8492. Min Act: -0.0001
Data Index: 1156717 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2904. Min Range: -2.2904
Max Act: 1.9722. Min Act: -0.0001
Data Index: 1465411 (Python Code)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2904. Min Range: -2.2904
Max Act: 1.9358. Min Act: -0.0001
Data Index: 1451595 (Python Code)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2904. Min Range: -2.2904
Max Act: 1.7275. Min Act: -0.0001
Data Index: 795160 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2904. Min Range: -2.2904
Max Act: 1.8905. Min Act: -0.0001
Data Index: 304238 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2904. Min Range: -2.2904
Max Act: 1.7792. Min Act: -0.0001
Data Index: 1198395 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2904. Min Range: -2.2904
Max Act: 1.8758. Min Act: -0.0001
Data Index: 707252 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19