Model: None
Dataset: The Pile
Neuron 2898 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 4.6329. Min Range: -4.6329
Max Act: 4.6329. Min Act: -0.1700
Data Index: 9291548 (The Pile)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6329. Min Range: -4.6329
Max Act: 4.6017. Min Act: -0.1700
Data Index: 9084835 (The Pile)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6329. Min Range: -4.6329
Max Act: 4.5704. Min Act: -0.1700
Data Index: 1717679 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6329. Min Range: -4.6329
Max Act: 4.5704. Min Act: -0.1700
Data Index: 844229 (The Pile)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6329. Min Range: -4.6329
Max Act: 4.5704. Min Act: -0.1700
Data Index: 8756555 (The Pile)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6329. Min Range: -4.6329
Max Act: 4.5704. Min Act: -0.1700
Data Index: 4428201 (The Pile)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6329. Min Range: -4.6329
Max Act: 4.5392. Min Act: -0.1700
Data Index: 10400735 (The Pile)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6329. Min Range: -4.6329
Max Act: 4.5392. Min Act: -0.1700
Data Index: 5275452 (The Pile)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6329. Min Range: -4.6329
Max Act: 4.5392. Min Act: -0.1700
Data Index: 2253617 (The Pile)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6329. Min Range: -4.6329
Max Act: 4.5392. Min Act: -0.1700
Data Index: 8923993 (The Pile)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6329. Min Range: -4.6329
Max Act: 4.5392. Min Act: -0.1700
Data Index: 8591576 (The Pile)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6329. Min Range: -4.6329
Max Act: 4.5392. Min Act: -0.1700
Data Index: 7367637 (The Pile)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6329. Min Range: -4.6329
Max Act: 4.5392. Min Act: -0.1700
Data Index: 446887 (The Pile)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6329. Min Range: -4.6329
Max Act: 4.5392. Min Act: -0.1700
Data Index: 3106741 (The Pile)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6329. Min Range: -4.6329
Max Act: 4.5079. Min Act: -0.1700
Data Index: 4798347 (The Pile)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6329. Min Range: -4.6329
Max Act: 4.5079. Min Act: -0.1700
Data Index: 2369546 (The Pile)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6329. Min Range: -4.6329
Max Act: 4.5079. Min Act: -0.1700
Data Index: 8986602 (The Pile)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6329. Min Range: -4.6329
Max Act: 4.5079. Min Act: -0.1699
Data Index: 1953072 (The Pile)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6329. Min Range: -4.6329
Max Act: 4.5079. Min Act: -0.1700
Data Index: 5907742 (The Pile)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6329. Min Range: -4.6329
Max Act: 4.5079. Min Act: -0.1700
Data Index: 9559755 (The Pile)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19