Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2240 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 1.2370. Min Range: -1.2370
Max Act: 1.1378. Min Act: -0.0001
Data Index: 1457509 (The Pile)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2370. Min Range: -1.2370
Max Act: 1.1615. Min Act: -0.0001
Data Index: 988248 (The Pile)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2370. Min Range: -1.2370
Max Act: 1.2292. Min Act: -0.0001
Data Index: 1401319 (The Pile)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2370. Min Range: -1.2370
Max Act: 1.2370. Min Act: -0.0001
Data Index: 836037 (The Pile)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2370. Min Range: -1.2370
Max Act: 1.0983. Min Act: -0.0001
Data Index: 1070574 (The Pile)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2370. Min Range: -1.2370
Max Act: 1.1069. Min Act: -0.0001
Data Index: 387131 (The Pile)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2370. Min Range: -1.2370
Max Act: 1.0679. Min Act: -0.0001
Data Index: 734969 (The Pile)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2370. Min Range: -1.2370
Max Act: 1.0872. Min Act: -0.0001
Data Index: 1576040 (The Pile)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2370. Min Range: -1.2370
Max Act: 1.0194. Min Act: -0.0001
Data Index: 741167 (The Pile)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2370. Min Range: -1.2370
Max Act: 1.0424. Min Act: -0.0001
Data Index: 121515 (The Pile)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2370. Min Range: -1.2370
Max Act: 1.0651. Min Act: -0.0001
Data Index: 246928 (The Pile)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2370. Min Range: -1.2370
Max Act: 1.0550. Min Act: -0.0001
Data Index: 936678 (The Pile)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2370. Min Range: -1.2370
Max Act: 0.9729. Min Act: -0.0001
Data Index: 1735433 (The Pile)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2370. Min Range: -1.2370
Max Act: 1.0046. Min Act: -0.0001
Data Index: 1383692 (The Pile)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2370. Min Range: -1.2370
Max Act: 0.9614. Min Act: -0.0001
Data Index: 262 (The Pile)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2370. Min Range: -1.2370
Max Act: 0.9387. Min Act: -0.0001
Data Index: 1279571 (The Pile)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2370. Min Range: -1.2370
Max Act: 1.0568. Min Act: -0.0001
Data Index: 119677 (The Pile)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2370. Min Range: -1.2370
Max Act: 0.9967. Min Act: -0.0001
Data Index: 445804 (The Pile)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2370. Min Range: -1.2370
Max Act: 0.9904. Min Act: -0.0001
Data Index: 1930373 (The Pile)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2370. Min Range: -1.2370
Max Act: 0.9314. Min Act: -0.0001
Data Index: 1517898 (The Pile)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19