Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3069 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.5470. Min Range: -1.5470
Max Act: 1.5470. Min Act: -0.0001
Data Index: 1376957 (The Pile)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5470. Min Range: -1.5470
Max Act: 1.5026. Min Act: -0.0001
Data Index: 1793609 (The Pile)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5470. Min Range: -1.5470
Max Act: 1.4232. Min Act: -0.0001
Data Index: 1483615 (The Pile)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5470. Min Range: -1.5470
Max Act: 1.1858. Min Act: -0.0001
Data Index: 134325 (The Pile)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5470. Min Range: -1.5470
Max Act: 1.4554. Min Act: -0.0001
Data Index: 244624 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5470. Min Range: -1.5470
Max Act: 1.2365. Min Act: -0.0001
Data Index: 1598030 (The Pile)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5470. Min Range: -1.5470
Max Act: 1.3943. Min Act: -0.0001
Data Index: 767500 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5470. Min Range: -1.5470
Max Act: 1.3363. Min Act: -0.0001
Data Index: 954396 (The Pile)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5470. Min Range: -1.5470
Max Act: 1.2379. Min Act: -0.0001
Data Index: 1136480 (The Pile)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5470. Min Range: -1.5470
Max Act: 1.1953. Min Act: -0.0001
Data Index: 384019 (The Pile)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5470. Min Range: -1.5470
Max Act: 1.2415. Min Act: -0.0001
Data Index: 1523343 (The Pile)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5470. Min Range: -1.5470
Max Act: 1.2992. Min Act: -0.0001
Data Index: 433311 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5470. Min Range: -1.5470
Max Act: 1.1224. Min Act: -0.0001
Data Index: 1285584 (The Pile)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5470. Min Range: -1.5470
Max Act: 1.1855. Min Act: -0.0001
Data Index: 1794123 (The Pile)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5470. Min Range: -1.5470
Max Act: 1.3166. Min Act: -0.0001
Data Index: 1107674 (The Pile)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5470. Min Range: -1.5470
Max Act: 1.1282. Min Act: -0.0001
Data Index: 241433 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5470. Min Range: -1.5470
Max Act: 1.2261. Min Act: -0.0001
Data Index: 597780 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5470. Min Range: -1.5470
Max Act: 1.0365. Min Act: -0.0001
Data Index: 61241 (The Pile)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5470. Min Range: -1.5470
Max Act: 1.0809. Min Act: -0.0001
Data Index: 1013887 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5470. Min Range: -1.5470
Max Act: 1.1083. Min Act: -0.0001
Data Index: 148063 (The Pile)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19