Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 76 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 3.4010. Min Range: -3.4010
Max Act: 3.4010. Min Act: -0.0000
Data Index: 588132 (The Pile)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4010. Min Range: -3.4010
Max Act: 3.3287. Min Act: -0.0000
Data Index: 7342 (The Pile)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4010. Min Range: -3.4010
Max Act: 3.2551. Min Act: -0.0000
Data Index: 146551 (The Pile)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4010. Min Range: -3.4010
Max Act: 3.3825. Min Act: -0.0000
Data Index: 1683064 (The Pile)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4010. Min Range: -3.4010
Max Act: 3.2177. Min Act: -0.0000
Data Index: 1045417 (The Pile)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4010. Min Range: -3.4010
Max Act: 3.1947. Min Act: -0.0000
Data Index: 1194844 (The Pile)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4010. Min Range: -3.4010
Max Act: 3.3029. Min Act: -0.0000
Data Index: 1165498 (The Pile)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4010. Min Range: -3.4010
Max Act: 3.1433. Min Act: -0.0000
Data Index: 441439 (The Pile)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4010. Min Range: -3.4010
Max Act: 3.1192. Min Act: -0.0000
Data Index: 1026622 (The Pile)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4010. Min Range: -3.4010
Max Act: 2.9368. Min Act: -0.0000
Data Index: 1802121 (The Pile)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4010. Min Range: -3.4010
Max Act: 3.1014. Min Act: -0.0000
Data Index: 1245579 (The Pile)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4010. Min Range: -3.4010
Max Act: 3.0567. Min Act: -0.0000
Data Index: 86169 (The Pile)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4010. Min Range: -3.4010
Max Act: 3.0010. Min Act: -0.0000
Data Index: 1334991 (The Pile)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4010. Min Range: -3.4010
Max Act: 2.7776. Min Act: -0.0000
Data Index: 584029 (The Pile)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4010. Min Range: -3.4010
Max Act: 2.8311. Min Act: -0.0000
Data Index: 1448523 (The Pile)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4010. Min Range: -3.4010
Max Act: 2.8892. Min Act: -0.0000
Data Index: 338195 (The Pile)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4010. Min Range: -3.4010
Max Act: 2.8523. Min Act: -0.0000
Data Index: 1015350 (The Pile)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4010. Min Range: -3.4010
Max Act: 2.8016. Min Act: -0.0000
Data Index: 647948 (The Pile)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4010. Min Range: -3.4010
Max Act: 2.8875. Min Act: -0.0000
Data Index: 1527250 (The Pile)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4010. Min Range: -3.4010
Max Act: 2.7595. Min Act: -0.0000
Data Index: 216516 (The Pile)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19