Model: None
Dataset: The Pile
Neuron 962 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.5314. Min Range: -3.5314
Max Act: 3.5314. Min Act: -0.1700
Data Index: 5840860 (The Pile)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5314. Min Range: -3.5314
Max Act: 3.2176. Min Act: -0.1700
Data Index: 4543123 (The Pile)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5314. Min Range: -3.5314
Max Act: 3.4217. Min Act: -0.1700
Data Index: 2107977 (The Pile)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5314. Min Range: -3.5314
Max Act: 3.2962. Min Act: -0.1700
Data Index: 3065215 (The Pile)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5314. Min Range: -3.5314
Max Act: 3.5001. Min Act: -0.1700
Data Index: 4346386 (The Pile)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5314. Min Range: -3.5314
Max Act: 3.3119. Min Act: -0.1700
Data Index: 109027 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5314. Min Range: -3.5314
Max Act: 3.4217. Min Act: -0.1699
Data Index: 10220115 (The Pile)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5314. Min Range: -3.5314
Max Act: 3.5314. Min Act: -0.1700
Data Index: 5663407 (The Pile)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5314. Min Range: -3.5314
Max Act: 3.3276. Min Act: -0.1700
Data Index: 472279 (The Pile)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5314. Min Range: -3.5314
Max Act: 3.3276. Min Act: -0.1700
Data Index: 9973160 (The Pile)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5314. Min Range: -3.5314
Max Act: 3.3590. Min Act: -0.1700
Data Index: 6504405 (The Pile)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5314. Min Range: -3.5314
Max Act: 3.5001. Min Act: -0.1700
Data Index: 9622650 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5314. Min Range: -3.5314
Max Act: 3.4687. Min Act: -0.1700
Data Index: 9946746 (The Pile)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5314. Min Range: -3.5314
Max Act: 3.2490. Min Act: -0.1699
Data Index: 9180780 (The Pile)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5314. Min Range: -3.5314
Max Act: 3.4217. Min Act: -0.1700
Data Index: 897315 (The Pile)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5314. Min Range: -3.5314
Max Act: 3.3747. Min Act: -0.1699
Data Index: 5175523 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5314. Min Range: -3.5314
Max Act: 3.4217. Min Act: -0.1700
Data Index: 7234192 (The Pile)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5314. Min Range: -3.5314
Max Act: 3.2490. Min Act: -0.1700
Data Index: 4061912 (The Pile)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5314. Min Range: -3.5314
Max Act: 3.3903. Min Act: -0.1700
Data Index: 8403877 (The Pile)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5314. Min Range: -3.5314
Max Act: 3.2962. Min Act: -0.1700
Data Index: 2835553 (The Pile)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19