Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1593 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0598. Min Range: -6.0598
Max Act: 6.0598. Min Act: -0.1700
Data Index: 2326121 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0598. Min Range: -6.0598
Max Act: 5.9036. Min Act: -0.1700
Data Index: 8623292 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0598. Min Range: -6.0598
Max Act: 5.7473. Min Act: -0.1700
Data Index: 4626065 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0598. Min Range: -6.0598
Max Act: 5.7161. Min Act: -0.1700
Data Index: 8281406 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0598. Min Range: -6.0598
Max Act: 5.6848. Min Act: -0.1700
Data Index: 1863001 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0598. Min Range: -6.0598
Max Act: 5.6848. Min Act: -0.1700
Data Index: 7282490 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0598. Min Range: -6.0598
Max Act: 5.6536. Min Act: -0.1700
Data Index: 4617565 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0598. Min Range: -6.0598
Max Act: 5.6848. Min Act: -0.1700
Data Index: 7399303 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0598. Min Range: -6.0598
Max Act: 5.6223. Min Act: -0.1700
Data Index: 2292884 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0598. Min Range: -6.0598
Max Act: 5.6536. Min Act: -0.1700
Data Index: 6748410 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0598. Min Range: -6.0598
Max Act: 5.6223. Min Act: -0.1700
Data Index: 2292882 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0598. Min Range: -6.0598
Max Act: 5.6223. Min Act: -0.1700
Data Index: 928113 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0598. Min Range: -6.0598
Max Act: 5.6223. Min Act: -0.1700
Data Index: 2929865 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0598. Min Range: -6.0598
Max Act: 5.5598. Min Act: -0.1700
Data Index: 19499 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0598. Min Range: -6.0598
Max Act: 5.5911. Min Act: -0.1700
Data Index: 3322347 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0598. Min Range: -6.0598
Max Act: 5.5911. Min Act: -0.1700
Data Index: 2292876 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0598. Min Range: -6.0598
Max Act: 5.4973. Min Act: -0.1700
Data Index: 1815200 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0598. Min Range: -6.0598
Max Act: 5.5286. Min Act: -0.1700
Data Index: 2292874 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0598. Min Range: -6.0598
Max Act: 5.5598. Min Act: -0.1700
Data Index: 2292881 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0598. Min Range: -6.0598
Max Act: 5.5598. Min Act: -0.1700
Data Index: 7471788 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19