Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3110 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.8059. Min Act: -0.0000
Data Index: 795496 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.6450. Min Act: -0.0000
Data Index: 1681944 (The Pile)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.3871. Min Act: -0.0000
Data Index: 261986 (The Pile)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.5861. Min Act: -0.0000
Data Index: 253375 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.3953. Min Act: -0.0000
Data Index: 137969 (The Pile)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.6397. Min Act: -0.0000
Data Index: 874948 (The Pile)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.4338. Min Act: -0.0000
Data Index: 1533947 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.3958. Min Act: -0.0000
Data Index: 1353316 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.3835. Min Act: -0.0000
Data Index: 1366298 (The Pile)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.3962. Min Act: -0.0000
Data Index: 632779 (The Pile)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.3031. Min Act: -0.0000
Data Index: 852350 (The Pile)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.0760. Min Act: -0.0000
Data Index: 573847 (The Pile)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.2767. Min Act: -0.0000
Data Index: 694105 (The Pile)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.2616. Min Act: -0.0000
Data Index: 1541319 (The Pile)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.3819. Min Act: -0.0000
Data Index: 296207 (The Pile)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.1380. Min Act: -0.0000
Data Index: 228948 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.2413. Min Act: -0.0000
Data Index: 215077 (The Pile)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.1292. Min Act: -0.0000
Data Index: 958978 (The Pile)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.1144. Min Act: -0.0000
Data Index: 1727080 (The Pile)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.2363. Min Act: -0.0000
Data Index: 356947 (The Pile)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19