Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1974 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.4693. Min Range: -3.4693
Max Act: 3.4146. Min Act: -0.0001
Data Index: 939667 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4693. Min Range: -3.4693
Max Act: 2.8265. Min Act: -0.0001
Data Index: 724847 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4693. Min Range: -3.4693
Max Act: 3.3305. Min Act: -0.0001
Data Index: 431658 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4693. Min Range: -3.4693
Max Act: 3.4693. Min Act: -0.0001
Data Index: 290362 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4693. Min Range: -3.4693
Max Act: 3.1292. Min Act: -0.0001
Data Index: 1285903 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4693. Min Range: -3.4693
Max Act: 3.0818. Min Act: -0.0001
Data Index: 195666 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4693. Min Range: -3.4693
Max Act: 2.6784. Min Act: -0.0001
Data Index: 897803 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4693. Min Range: -3.4693
Max Act: 2.3866. Min Act: -0.0001
Data Index: 828732 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4693. Min Range: -3.4693
Max Act: 2.4330. Min Act: -0.0001
Data Index: 1187655 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4693. Min Range: -3.4693
Max Act: 2.6836. Min Act: -0.0001
Data Index: 791899 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4693. Min Range: -3.4693
Max Act: 2.1457. Min Act: -0.0001
Data Index: 878341 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4693. Min Range: -3.4693
Max Act: 2.1465. Min Act: -0.0001
Data Index: 273401 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4693. Min Range: -3.4693
Max Act: 2.0126. Min Act: -0.0001
Data Index: 816619 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4693. Min Range: -3.4693
Max Act: 2.2469. Min Act: -0.0001
Data Index: 1291488 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4693. Min Range: -3.4693
Max Act: 2.0120. Min Act: -0.0001
Data Index: 743108 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4693. Min Range: -3.4693
Max Act: 2.1256. Min Act: -0.0001
Data Index: 438256 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4693. Min Range: -3.4693
Max Act: 2.0060. Min Act: -0.0001
Data Index: 787180 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4693. Min Range: -3.4693
Max Act: 1.8302. Min Act: -0.0001
Data Index: 37943 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4693. Min Range: -3.4693
Max Act: 1.9343. Min Act: -0.0001
Data Index: 1252598 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4693. Min Range: -3.4693
Max Act: 1.9760. Min Act: -0.0001
Data Index: 684323 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19