Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2456 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.4458. Min Range: -1.4458
Max Act: 1.4458. Min Act: 0.0000
Data Index: 1180280 (The Pile)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4458. Min Range: -1.4458
Max Act: 1.3601. Min Act: 0.0000
Data Index: 404275 (The Pile)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4458. Min Range: -1.4458
Max Act: 1.3148. Min Act: -0.0000
Data Index: 1188133 (The Pile)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4458. Min Range: -1.4458
Max Act: 1.3668. Min Act: -0.0000
Data Index: 1804702 (The Pile)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4458. Min Range: -1.4458
Max Act: 1.2333. Min Act: -0.0000
Data Index: 1783817 (The Pile)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4458. Min Range: -1.4458
Max Act: 1.2336. Min Act: -0.0000
Data Index: 1862294 (The Pile)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4458. Min Range: -1.4458
Max Act: 1.2768. Min Act: -0.0000
Data Index: 1372144 (The Pile)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4458. Min Range: -1.4458
Max Act: 1.0629. Min Act: 0.0000
Data Index: 1098097 (The Pile)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4458. Min Range: -1.4458
Max Act: 1.0480. Min Act: -0.0000
Data Index: 1916729 (The Pile)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4458. Min Range: -1.4458
Max Act: 1.0761. Min Act: -0.0000
Data Index: 1255526 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4458. Min Range: -1.4458
Max Act: 1.0624. Min Act: 0.0000
Data Index: 22270 (The Pile)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4458. Min Range: -1.4458
Max Act: 1.0598. Min Act: -0.0000
Data Index: 377001 (The Pile)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4458. Min Range: -1.4458
Max Act: 1.0602. Min Act: 0.0000
Data Index: 353019 (The Pile)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4458. Min Range: -1.4458
Max Act: 1.0617. Min Act: 0.0001
Data Index: 869251 (The Pile)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4458. Min Range: -1.4458
Max Act: 1.0542. Min Act: -0.0000
Data Index: 504172 (The Pile)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4458. Min Range: -1.4458
Max Act: 1.0230. Min Act: 0.0000
Data Index: 292601 (The Pile)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4458. Min Range: -1.4458
Max Act: 1.0164. Min Act: 0.0000
Data Index: 1471439 (The Pile)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4458. Min Range: -1.4458
Max Act: 0.9772. Min Act: -0.0000
Data Index: 1639456 (The Pile)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4458. Min Range: -1.4458
Max Act: 1.0351. Min Act: -0.0000
Data Index: 1544385 (The Pile)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4458. Min Range: -1.4458
Max Act: 0.9276. Min Act: -0.0000
Data Index: 1020846 (The Pile)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19