Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1226 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.3444. Min Range: -9.3444
Max Act: 9.3444. Min Act: -0.1700
Data Index: 1447895 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3444. Min Range: -9.3444
Max Act: 9.2194. Min Act: -0.1700
Data Index: 4937020 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3444. Min Range: -9.3444
Max Act: 9.0319. Min Act: -0.1700
Data Index: 6070543 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3444. Min Range: -9.3444
Max Act: 8.9694. Min Act: -0.1700
Data Index: 3941430 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3444. Min Range: -9.3444
Max Act: 9.0319. Min Act: -0.1700
Data Index: 3452674 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3444. Min Range: -9.3444
Max Act: 8.9694. Min Act: -0.1700
Data Index: 2887347 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3444. Min Range: -9.3444
Max Act: 8.8444. Min Act: -0.1700
Data Index: 567871 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3444. Min Range: -9.3444
Max Act: 8.8444. Min Act: -0.1700
Data Index: 2909241 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3444. Min Range: -9.3444
Max Act: 8.8444. Min Act: -0.1700
Data Index: 7863111 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3444. Min Range: -9.3444
Max Act: 8.7819. Min Act: -0.1700
Data Index: 1012637 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3444. Min Range: -9.3444
Max Act: 8.8444. Min Act: -0.1700
Data Index: 2270633 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3444. Min Range: -9.3444
Max Act: 8.7194. Min Act: -0.1700
Data Index: 7250174 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3444. Min Range: -9.3444
Max Act: 8.7819. Min Act: -0.1700
Data Index: 5338880 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3444. Min Range: -9.3444
Max Act: 8.7194. Min Act: -0.1700
Data Index: 6656945 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3444. Min Range: -9.3444
Max Act: 8.6569. Min Act: -0.1700
Data Index: 6656943 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3444. Min Range: -9.3444
Max Act: 8.6569. Min Act: -0.1700
Data Index: 6656944 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3444. Min Range: -9.3444
Max Act: 8.6569. Min Act: -0.1700
Data Index: 1012639 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3444. Min Range: -9.3444
Max Act: 8.6569. Min Act: -0.1700
Data Index: 1417296 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3444. Min Range: -9.3444
Max Act: 8.7194. Min Act: -0.1700
Data Index: 3736694 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3444. Min Range: -9.3444
Max Act: 8.5944. Min Act: -0.1700
Data Index: 5563879 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19