Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 304 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.3400. Min Range: -1.3400
Max Act: 1.3400. Min Act: -0.0001
Data Index: 335931 (The Pile)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3400. Min Range: -1.3400
Max Act: 1.2537. Min Act: -0.0001
Data Index: 521429 (The Pile)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3400. Min Range: -1.3400
Max Act: 1.1966. Min Act: -0.0001
Data Index: 1678859 (The Pile)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3400. Min Range: -1.3400
Max Act: 1.2116. Min Act: -0.0001
Data Index: 319959 (The Pile)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3400. Min Range: -1.3400
Max Act: 1.2212. Min Act: -0.0001
Data Index: 884660 (The Pile)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3400. Min Range: -1.3400
Max Act: 1.2032. Min Act: -0.0001
Data Index: 1990228 (The Pile)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3400. Min Range: -1.3400
Max Act: 1.2402. Min Act: -0.0001
Data Index: 468669 (The Pile)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3400. Min Range: -1.3400
Max Act: 1.1685. Min Act: -0.0001
Data Index: 1144704 (The Pile)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3400. Min Range: -1.3400
Max Act: 1.1422. Min Act: -0.0001
Data Index: 1495604 (The Pile)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3400. Min Range: -1.3400
Max Act: 1.1524. Min Act: -0.0001
Data Index: 1433735 (The Pile)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3400. Min Range: -1.3400
Max Act: 0.9841. Min Act: -0.0001
Data Index: 1607204 (The Pile)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3400. Min Range: -1.3400
Max Act: 1.0904. Min Act: -0.0001
Data Index: 1082334 (The Pile)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3400. Min Range: -1.3400
Max Act: 1.1073. Min Act: -0.0001
Data Index: 53254 (The Pile)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3400. Min Range: -1.3400
Max Act: 1.1333. Min Act: -0.0001
Data Index: 1223455 (The Pile)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3400. Min Range: -1.3400
Max Act: 1.1317. Min Act: -0.0001
Data Index: 4754 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3400. Min Range: -1.3400
Max Act: 1.0976. Min Act: -0.0001
Data Index: 1438351 (The Pile)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3400. Min Range: -1.3400
Max Act: 1.1628. Min Act: -0.0001
Data Index: 163361 (The Pile)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3400. Min Range: -1.3400
Max Act: 1.0372. Min Act: -0.0001
Data Index: 373376 (The Pile)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3400. Min Range: -1.3400
Max Act: 1.0607. Min Act: -0.0001
Data Index: 1939955 (The Pile)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3400. Min Range: -1.3400
Max Act: 1.0338. Min Act: -0.0001
Data Index: 869988 (The Pile)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19