Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3512 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3443. Min Range: -6.3443
Max Act: 6.3443. Min Act: -0.1700
Data Index: 7143794 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3443. Min Range: -6.3443
Max Act: 6.3131. Min Act: -0.1700
Data Index: 2248348 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3443. Min Range: -6.3443
Max Act: 6.2193. Min Act: -0.1700
Data Index: 2420081 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3443. Min Range: -6.3443
Max Act: 6.1881. Min Act: -0.1700
Data Index: 6560374 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3443. Min Range: -6.3443
Max Act: 6.1568. Min Act: -0.1700
Data Index: 2570500 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3443. Min Range: -6.3443
Max Act: 6.0943. Min Act: -0.1700
Data Index: 7766768 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3443. Min Range: -6.3443
Max Act: 6.0631. Min Act: -0.1700
Data Index: 4364755 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3443. Min Range: -6.3443
Max Act: 6.0631. Min Act: -0.1700
Data Index: 5438009 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3443. Min Range: -6.3443
Max Act: 6.0631. Min Act: -0.1700
Data Index: 6451893 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3443. Min Range: -6.3443
Max Act: 6.0318. Min Act: -0.1700
Data Index: 164196 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3443. Min Range: -6.3443
Max Act: 6.0006. Min Act: -0.1700
Data Index: 8003332 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3443. Min Range: -6.3443
Max Act: 6.0318. Min Act: -0.1700
Data Index: 7038735 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3443. Min Range: -6.3443
Max Act: 6.0006. Min Act: -0.1700
Data Index: 5275373 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3443. Min Range: -6.3443
Max Act: 6.0006. Min Act: -0.1700
Data Index: 5580187 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3443. Min Range: -6.3443
Max Act: 5.9693. Min Act: -0.1700
Data Index: 5032692 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3443. Min Range: -6.3443
Max Act: 5.9381. Min Act: -0.1700
Data Index: 4797498 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3443. Min Range: -6.3443
Max Act: 5.9381. Min Act: -0.1700
Data Index: 8089213 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3443. Min Range: -6.3443
Max Act: 5.9068. Min Act: -0.1700
Data Index: 7210420 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3443. Min Range: -6.3443
Max Act: 5.9068. Min Act: -0.1700
Data Index: 1669864 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3443. Min Range: -6.3443
Max Act: 5.8756. Min Act: -0.1700
Data Index: 7329782 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19