Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 511 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.0305. Min Range: -1.0305
Max Act: 1.0305. Min Act: -0.0001
Data Index: 323652 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0305. Min Range: -1.0305
Max Act: 0.8711. Min Act: -0.0001
Data Index: 1807762 (The Pile)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0305. Min Range: -1.0305
Max Act: 0.8543. Min Act: -0.0001
Data Index: 49700 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0305. Min Range: -1.0305
Max Act: 0.8278. Min Act: -0.0001
Data Index: 1161068 (The Pile)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0305. Min Range: -1.0305
Max Act: 0.8559. Min Act: -0.0001
Data Index: 1573560 (The Pile)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0305. Min Range: -1.0305
Max Act: 0.7012. Min Act: -0.0001
Data Index: 246293 (The Pile)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0305. Min Range: -1.0305
Max Act: 0.7429. Min Act: -0.0001
Data Index: 531880 (The Pile)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0305. Min Range: -1.0305
Max Act: 0.8162. Min Act: -0.0001
Data Index: 409085 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0305. Min Range: -1.0305
Max Act: 0.7834. Min Act: -0.0001
Data Index: 879441 (The Pile)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0305. Min Range: -1.0305
Max Act: 0.7311. Min Act: -0.0001
Data Index: 311292 (The Pile)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0305. Min Range: -1.0305
Max Act: 0.8133. Min Act: -0.0001
Data Index: 1813858 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0305. Min Range: -1.0305
Max Act: 0.8120. Min Act: -0.0001
Data Index: 112671 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0305. Min Range: -1.0305
Max Act: 0.7775. Min Act: -0.0001
Data Index: 1891957 (The Pile)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0305. Min Range: -1.0305
Max Act: 0.7313. Min Act: -0.0001
Data Index: 323836 (The Pile)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0305. Min Range: -1.0305
Max Act: 0.7283. Min Act: -0.0001
Data Index: 1104606 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0305. Min Range: -1.0305
Max Act: 0.7451. Min Act: -0.0001
Data Index: 1540962 (The Pile)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0305. Min Range: -1.0305
Max Act: 0.7452. Min Act: -0.0001
Data Index: 1984896 (The Pile)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0305. Min Range: -1.0305
Max Act: 0.7654. Min Act: -0.0001
Data Index: 1215446 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0305. Min Range: -1.0305
Max Act: 0.8970. Min Act: -0.0001
Data Index: 1851289 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0305. Min Range: -1.0305
Max Act: 0.7700. Min Act: -0.0001
Data Index: 1719527 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19