Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2130 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.0135. Min Range: -0.0135
Max Act: 0.0135. Min Act: -0.0002
Data Index: 1606163 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0135. Min Range: -0.0135
Max Act: 0.0133. Min Act: -0.0002
Data Index: 1694449 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0135. Min Range: -0.0135
Max Act: 0.0130. Min Act: -0.0002
Data Index: 184589 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0135. Min Range: -0.0135
Max Act: 0.0130. Min Act: -0.0002
Data Index: 869551 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0135. Min Range: -0.0135
Max Act: 0.0130. Min Act: -0.0002
Data Index: 782932 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0135. Min Range: -0.0135
Max Act: 0.0130. Min Act: -0.0002
Data Index: 393836 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0135. Min Range: -0.0135
Max Act: 0.0130. Min Act: -0.0002
Data Index: 384883 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0135. Min Range: -0.0135
Max Act: 0.0130. Min Act: -0.0002
Data Index: 381667 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0135. Min Range: -0.0135
Max Act: 0.0130. Min Act: -0.0002
Data Index: 376396 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0135. Min Range: -0.0135
Max Act: 0.0130. Min Act: -0.0002
Data Index: 121524 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0135. Min Range: -0.0135
Max Act: 0.0130. Min Act: -0.0002
Data Index: 887850 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0135. Min Range: -0.0135
Max Act: 0.0130. Min Act: -0.0002
Data Index: 759763 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0135. Min Range: -0.0135
Max Act: 0.0130. Min Act: -0.0002
Data Index: 116409 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0135. Min Range: -0.0135
Max Act: 0.0130. Min Act: -0.0002
Data Index: 311236 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0135. Min Range: -0.0135
Max Act: 0.0130. Min Act: -0.0002
Data Index: 747251 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0135. Min Range: -0.0135
Max Act: 0.0130. Min Act: -0.0002
Data Index: 79288 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0135. Min Range: -0.0135
Max Act: 0.0130. Min Act: -0.0002
Data Index: 718399 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0135. Min Range: -0.0135
Max Act: 0.0130. Min Act: -0.0002
Data Index: 639040 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0135. Min Range: -0.0135
Max Act: 0.0130. Min Act: -0.0002
Data Index: 563019 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0135. Min Range: -0.0135
Max Act: 0.0130. Min Act: -0.0002
Data Index: 524623 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19