Model: None
Dataset: The Pile
Neuron 2014 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.9897. Min Range: -2.9897
Max Act: 2.9897. Min Act: -0.1700
Data Index: 3651959 (The Pile)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9897. Min Range: -2.9897
Max Act: 2.9897. Min Act: -0.1700
Data Index: 10514641 (The Pile)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9897. Min Range: -2.9897
Max Act: 2.9422. Min Act: -0.1700
Data Index: 2196463 (The Pile)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9897. Min Range: -2.9897
Max Act: 2.9581. Min Act: -0.1700
Data Index: 8331589 (The Pile)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9897. Min Range: -2.9897
Max Act: 2.9581. Min Act: -0.1700
Data Index: 3648640 (The Pile)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9897. Min Range: -2.9897
Max Act: 2.9422. Min Act: -0.1700
Data Index: 6197326 (The Pile)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9897. Min Range: -2.9897
Max Act: 2.9264. Min Act: -0.1700
Data Index: 8285615 (The Pile)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9897. Min Range: -2.9897
Max Act: 2.9264. Min Act: -0.1700
Data Index: 9948323 (The Pile)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9897. Min Range: -2.9897
Max Act: 2.8947. Min Act: -0.1700
Data Index: 2859284 (The Pile)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9897. Min Range: -2.9897
Max Act: 2.9422. Min Act: -0.1700
Data Index: 6313945 (The Pile)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9897. Min Range: -2.9897
Max Act: 2.9264. Min Act: -0.1700
Data Index: 1503375 (The Pile)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9897. Min Range: -2.9897
Max Act: 2.9264. Min Act: -0.1700
Data Index: 820022 (The Pile)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9897. Min Range: -2.9897
Max Act: 2.9264. Min Act: -0.1700
Data Index: 4844166 (The Pile)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9897. Min Range: -2.9897
Max Act: 2.9264. Min Act: -0.1700
Data Index: 9646769 (The Pile)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9897. Min Range: -2.9897
Max Act: 2.9264. Min Act: -0.1700
Data Index: 4374927 (The Pile)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9897. Min Range: -2.9897
Max Act: 2.9105. Min Act: -0.1700
Data Index: 3197454 (The Pile)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9897. Min Range: -2.9897
Max Act: 2.9264. Min Act: -0.1700
Data Index: 8513344 (The Pile)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9897. Min Range: -2.9897
Max Act: 2.9105. Min Act: -0.1700
Data Index: 4222983 (The Pile)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9897. Min Range: -2.9897
Max Act: 2.9105. Min Act: -0.1700
Data Index: 7660432 (The Pile)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9897. Min Range: -2.9897
Max Act: 2.9105. Min Act: -0.1700
Data Index: 5628928 (The Pile)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19