Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1814 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0618. Min Range: -5.0618
Max Act: 5.0618. Min Act: -0.1700
Data Index: 6490294 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0618. Min Range: -5.0618
Max Act: 5.0305. Min Act: -0.1700
Data Index: 6950579 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0618. Min Range: -5.0618
Max Act: 5.0305. Min Act: -0.1700
Data Index: 7520717 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0618. Min Range: -5.0618
Max Act: 5.0305. Min Act: -0.1700
Data Index: 637681 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0618. Min Range: -5.0618
Max Act: 4.9993. Min Act: -0.1700
Data Index: 7022679 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0618. Min Range: -5.0618
Max Act: 4.9680. Min Act: -0.1700
Data Index: 4132991 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0618. Min Range: -5.0618
Max Act: 4.9680. Min Act: -0.1700
Data Index: 4155741 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0618. Min Range: -5.0618
Max Act: 4.9680. Min Act: -0.1700
Data Index: 4466316 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0618. Min Range: -5.0618
Max Act: 4.9680. Min Act: -0.1700
Data Index: 3789928 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0618. Min Range: -5.0618
Max Act: 4.9368. Min Act: -0.1700
Data Index: 6053637 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0618. Min Range: -5.0618
Max Act: 4.9055. Min Act: -0.1700
Data Index: 8096212 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0618. Min Range: -5.0618
Max Act: 4.9680. Min Act: -0.1700
Data Index: 4099392 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0618. Min Range: -5.0618
Max Act: 4.9368. Min Act: -0.1700
Data Index: 6873557 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0618. Min Range: -5.0618
Max Act: 4.9680. Min Act: -0.1700
Data Index: 2880318 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0618. Min Range: -5.0618
Max Act: 4.9368. Min Act: -0.1700
Data Index: 8212426 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0618. Min Range: -5.0618
Max Act: 4.9055. Min Act: -0.1700
Data Index: 4296747 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0618. Min Range: -5.0618
Max Act: 4.9055. Min Act: -0.1700
Data Index: 4279539 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0618. Min Range: -5.0618
Max Act: 4.9055. Min Act: -0.1700
Data Index: 609977 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0618. Min Range: -5.0618
Max Act: 4.9055. Min Act: -0.1700
Data Index: 3346434 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0618. Min Range: -5.0618
Max Act: 4.9055. Min Act: -0.1700
Data Index: 1284682 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19