Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2802 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.3010. Min Range: -2.3010
Max Act: 2.3010. Min Act: -0.0000
Data Index: 781551 (The Pile)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3010. Min Range: -2.3010
Max Act: 2.2909. Min Act: -0.0000
Data Index: 894375 (The Pile)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3010. Min Range: -2.3010
Max Act: 2.0836. Min Act: -0.0000
Data Index: 866292 (The Pile)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3010. Min Range: -2.3010
Max Act: 2.1430. Min Act: -0.0000
Data Index: 801119 (The Pile)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3010. Min Range: -2.3010
Max Act: 2.1562. Min Act: -0.0000
Data Index: 975696 (The Pile)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3010. Min Range: -2.3010
Max Act: 2.1929. Min Act: -0.0000
Data Index: 1764308 (The Pile)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3010. Min Range: -2.3010
Max Act: 2.0601. Min Act: -0.0000
Data Index: 1604772 (The Pile)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3010. Min Range: -2.3010
Max Act: 1.9741. Min Act: -0.0000
Data Index: 944231 (The Pile)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3010. Min Range: -2.3010
Max Act: 1.9681. Min Act: -0.0000
Data Index: 57080 (The Pile)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3010. Min Range: -2.3010
Max Act: 1.9342. Min Act: -0.0000
Data Index: 601953 (The Pile)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3010. Min Range: -2.3010
Max Act: 1.8505. Min Act: -0.0000
Data Index: 1106960 (The Pile)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3010. Min Range: -2.3010
Max Act: 1.8381. Min Act: -0.0000
Data Index: 1989111 (The Pile)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3010. Min Range: -2.3010
Max Act: 2.0384. Min Act: -0.0000
Data Index: 169639 (The Pile)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3010. Min Range: -2.3010
Max Act: 1.8213. Min Act: -0.0000
Data Index: 1103141 (The Pile)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3010. Min Range: -2.3010
Max Act: 1.8026. Min Act: -0.0000
Data Index: 509192 (The Pile)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3010. Min Range: -2.3010
Max Act: 1.9003. Min Act: -0.0000
Data Index: 1503268 (The Pile)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3010. Min Range: -2.3010
Max Act: 1.8916. Min Act: -0.0000
Data Index: 463760 (The Pile)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3010. Min Range: -2.3010
Max Act: 1.7939. Min Act: -0.0000
Data Index: 60115 (The Pile)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3010. Min Range: -2.3010
Max Act: 1.8463. Min Act: -0.0000
Data Index: 236300 (The Pile)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3010. Min Range: -2.3010
Max Act: 1.7603. Min Act: -0.0000
Data Index: 879172 (The Pile)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19