Model: None
Dataset: The Pile
Neuron 2722 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.3064. Min Range: -3.3064
Max Act: 3.3064. Min Act: -0.1700
Data Index: 2606218 (The Pile)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3064. Min Range: -3.3064
Max Act: 3.2750. Min Act: -0.1700
Data Index: 10746918 (The Pile)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3064. Min Range: -3.3064
Max Act: 3.2435. Min Act: -0.1700
Data Index: 6269635 (The Pile)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3064. Min Range: -3.3064
Max Act: 3.1491. Min Act: -0.1700
Data Index: 185449 (The Pile)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3064. Min Range: -3.3064
Max Act: 3.1491. Min Act: -0.1700
Data Index: 8388142 (The Pile)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3064. Min Range: -3.3064
Max Act: 3.0545. Min Act: -0.1700
Data Index: 1214268 (The Pile)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3064. Min Range: -3.3064
Max Act: 3.0388. Min Act: -0.1700
Data Index: 2896632 (The Pile)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3064. Min Range: -3.3064
Max Act: 3.0072. Min Act: -0.1700
Data Index: 5377434 (The Pile)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3064. Min Range: -3.3064
Max Act: 3.0072. Min Act: -0.1700
Data Index: 6758576 (The Pile)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3064. Min Range: -3.3064
Max Act: 3.0072. Min Act: -0.1700
Data Index: 3936001 (The Pile)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3064. Min Range: -3.3064
Max Act: 3.0072. Min Act: -0.1700
Data Index: 8012846 (The Pile)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3064. Min Range: -3.3064
Max Act: 3.0072. Min Act: -0.1700
Data Index: 5135750 (The Pile)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3064. Min Range: -3.3064
Max Act: 2.9913. Min Act: -0.1700
Data Index: 2786728 (The Pile)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3064. Min Range: -3.3064
Max Act: 2.9913. Min Act: -0.1700
Data Index: 2890984 (The Pile)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3064. Min Range: -3.3064
Max Act: 2.9755. Min Act: -0.1700
Data Index: 6656338 (The Pile)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3064. Min Range: -3.3064
Max Act: 2.9755. Min Act: -0.1700
Data Index: 1027392 (The Pile)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3064. Min Range: -3.3064
Max Act: 2.9597. Min Act: -0.1700
Data Index: 5031044 (The Pile)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3064. Min Range: -3.3064
Max Act: 2.9597. Min Act: -0.1700
Data Index: 10486097 (The Pile)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3064. Min Range: -3.3064
Max Act: 2.9597. Min Act: -0.1700
Data Index: 3401191 (The Pile)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3064. Min Range: -3.3064
Max Act: 2.9439. Min Act: -0.1700
Data Index: 5750575 (The Pile)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19