Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 0 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.3676. Min Range: -1.3676
Max Act: 1.3676. Min Act: -0.0001
Data Index: 126595 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3676. Min Range: -1.3676
Max Act: 1.2842. Min Act: -0.0001
Data Index: 868419 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3676. Min Range: -1.3676
Max Act: 1.3076. Min Act: -0.0001
Data Index: 833120 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3676. Min Range: -1.3676
Max Act: 1.2731. Min Act: -0.0001
Data Index: 974664 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3676. Min Range: -1.3676
Max Act: 1.1928. Min Act: -0.0001
Data Index: 947854 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3676. Min Range: -1.3676
Max Act: 1.1385. Min Act: -0.0001
Data Index: 1299990 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3676. Min Range: -1.3676
Max Act: 1.2590. Min Act: -0.0001
Data Index: 750634 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3676. Min Range: -1.3676
Max Act: 1.1219. Min Act: -0.0001
Data Index: 784903 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3676. Min Range: -1.3676
Max Act: 1.0697. Min Act: -0.0001
Data Index: 1293744 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3676. Min Range: -1.3676
Max Act: 1.1294. Min Act: -0.0001
Data Index: 1014154 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3676. Min Range: -1.3676
Max Act: 1.0918. Min Act: -0.0001
Data Index: 28025 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3676. Min Range: -1.3676
Max Act: 1.1556. Min Act: -0.0001
Data Index: 726175 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3676. Min Range: -1.3676
Max Act: 1.0519. Min Act: -0.0001
Data Index: 985148 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3676. Min Range: -1.3676
Max Act: 1.0903. Min Act: -0.0001
Data Index: 1040050 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3676. Min Range: -1.3676
Max Act: 1.0933. Min Act: -0.0001
Data Index: 444813 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3676. Min Range: -1.3676
Max Act: 1.1441. Min Act: -0.0001
Data Index: 739589 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3676. Min Range: -1.3676
Max Act: 1.1098. Min Act: -0.0001
Data Index: 832287 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3676. Min Range: -1.3676
Max Act: 1.0107. Min Act: -0.0001
Data Index: 1288773 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3676. Min Range: -1.3676
Max Act: 1.0310. Min Act: -0.0001
Data Index: 1023215 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3676. Min Range: -1.3676
Max Act: 1.0238. Min Act: -0.0001
Data Index: 222075 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19