Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2730 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.6552. Min Act: 0.0001
Data Index: 513059 (The Pile)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4422. Min Act: -0.0000
Data Index: 1383089 (The Pile)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.1480. Min Act: -0.0000
Data Index: 924206 (The Pile)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.3575. Min Act: 0.0000
Data Index: 1070064 (The Pile)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.2020. Min Act: 0.0001
Data Index: 620059 (The Pile)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6552. Min Range: -4.6552
Max Act: 3.9871. Min Act: -0.0000
Data Index: 1319011 (The Pile)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6552. Min Range: -4.6552
Max Act: 3.3048. Min Act: 0.0001
Data Index: 1898304 (The Pile)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6552. Min Range: -4.6552
Max Act: 3.5912. Min Act: 0.0001
Data Index: 519756 (The Pile)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6552. Min Range: -4.6552
Max Act: 3.7096. Min Act: -0.0000
Data Index: 903766 (The Pile)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.0711. Min Act: 0.0001
Data Index: 1774464 (The Pile)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6552. Min Range: -4.6552
Max Act: 3.6484. Min Act: 0.0000
Data Index: 952346 (The Pile)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6552. Min Range: -4.6552
Max Act: 3.6537. Min Act: 0.0001
Data Index: 986302 (The Pile)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6552. Min Range: -4.6552
Max Act: 3.8894. Min Act: 0.0000
Data Index: 1571529 (The Pile)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6552. Min Range: -4.6552
Max Act: 3.5227. Min Act: 0.0001
Data Index: 1104036 (The Pile)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6552. Min Range: -4.6552
Max Act: 3.7125. Min Act: 0.0000
Data Index: 1006483 (The Pile)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6552. Min Range: -4.6552
Max Act: 3.8192. Min Act: 0.0001
Data Index: 965314 (The Pile)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6552. Min Range: -4.6552
Max Act: 3.6692. Min Act: 0.0000
Data Index: 923298 (The Pile)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6552. Min Range: -4.6552
Max Act: 3.8098. Min Act: 0.0001
Data Index: 1093660 (The Pile)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6552. Min Range: -4.6552
Max Act: 3.6008. Min Act: 0.0001
Data Index: 803624 (The Pile)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6552. Min Range: -4.6552
Max Act: 3.5839. Min Act: 0.0001
Data Index: 238165 (The Pile)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19