Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 6140 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.3208. Min Range: -3.3208
Max Act: 3.3208. Min Act: -0.0001
Data Index: 875630 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3208. Min Range: -3.3208
Max Act: 3.0673. Min Act: -0.0001
Data Index: 92282 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3208. Min Range: -3.3208
Max Act: 2.8014. Min Act: -0.0001
Data Index: 340685 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3208. Min Range: -3.3208
Max Act: 2.9456. Min Act: -0.0001
Data Index: 840845 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3208. Min Range: -3.3208
Max Act: 2.9454. Min Act: -0.0001
Data Index: 800990 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3208. Min Range: -3.3208
Max Act: 2.8358. Min Act: -0.0001
Data Index: 834247 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3208. Min Range: -3.3208
Max Act: 2.5625. Min Act: -0.0001
Data Index: 587479 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3208. Min Range: -3.3208
Max Act: 2.8323. Min Act: -0.0001
Data Index: 101952 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3208. Min Range: -3.3208
Max Act: 2.5241. Min Act: -0.0001
Data Index: 1141304 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3208. Min Range: -3.3208
Max Act: 2.4440. Min Act: -0.0001
Data Index: 1335980 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3208. Min Range: -3.3208
Max Act: 2.5489. Min Act: -0.0001
Data Index: 1129376 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3208. Min Range: -3.3208
Max Act: 2.5410. Min Act: -0.0001
Data Index: 282637 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3208. Min Range: -3.3208
Max Act: 2.6273. Min Act: -0.0001
Data Index: 933606 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3208. Min Range: -3.3208
Max Act: 2.4996. Min Act: -0.0001
Data Index: 857489 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3208. Min Range: -3.3208
Max Act: 2.3423. Min Act: -0.0001
Data Index: 591836 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3208. Min Range: -3.3208
Max Act: 2.3329. Min Act: -0.0001
Data Index: 6591 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3208. Min Range: -3.3208
Max Act: 2.5519. Min Act: -0.0001
Data Index: 413478 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3208. Min Range: -3.3208
Max Act: 2.6277. Min Act: -0.0001
Data Index: 246074 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3208. Min Range: -3.3208
Max Act: 2.3776. Min Act: -0.0001
Data Index: 1088177 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3208. Min Range: -3.3208
Max Act: 2.3551. Min Act: -0.0001
Data Index: 114157 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19