Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5015 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0484. Min Range: -5.0484
Max Act: 5.0484. Min Act: -0.1700
Data Index: 2059718 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0484. Min Range: -5.0484
Max Act: 5.0484. Min Act: -0.1700
Data Index: 8689681 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0484. Min Range: -5.0484
Max Act: 5.0172. Min Act: -0.1700
Data Index: 1667894 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0484. Min Range: -5.0484
Max Act: 4.9859. Min Act: -0.1700
Data Index: 1148433 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0484. Min Range: -5.0484
Max Act: 4.9547. Min Act: -0.1700
Data Index: 3315416 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0484. Min Range: -5.0484
Max Act: 4.9234. Min Act: -0.1700
Data Index: 12546 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0484. Min Range: -5.0484
Max Act: 4.9234. Min Act: -0.1700
Data Index: 1870922 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0484. Min Range: -5.0484
Max Act: 4.9234. Min Act: -0.1700
Data Index: 2857151 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0484. Min Range: -5.0484
Max Act: 4.9234. Min Act: -0.1700
Data Index: 8183695 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0484. Min Range: -5.0484
Max Act: 4.8609. Min Act: -0.1700
Data Index: 1204032 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0484. Min Range: -5.0484
Max Act: 4.8922. Min Act: -0.1700
Data Index: 6186676 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0484. Min Range: -5.0484
Max Act: 4.8922. Min Act: -0.1700
Data Index: 772988 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0484. Min Range: -5.0484
Max Act: 4.8922. Min Act: -0.1700
Data Index: 6536936 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0484. Min Range: -5.0484
Max Act: 4.8922. Min Act: -0.1700
Data Index: 3883367 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0484. Min Range: -5.0484
Max Act: 4.8922. Min Act: -0.1700
Data Index: 8477728 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0484. Min Range: -5.0484
Max Act: 4.8922. Min Act: -0.1700
Data Index: 7425561 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0484. Min Range: -5.0484
Max Act: 4.8609. Min Act: -0.1700
Data Index: 708151 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0484. Min Range: -5.0484
Max Act: 4.8609. Min Act: -0.1700
Data Index: 6618958 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0484. Min Range: -5.0484
Max Act: 4.8609. Min Act: -0.1700
Data Index: 347823 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0484. Min Range: -5.0484
Max Act: 4.8609. Min Act: -0.1700
Data Index: 4744769 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19