Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2981 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1361. Min Range: -8.1361
Max Act: 8.1361. Min Act: -0.1700
Data Index: 5876385 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1361. Min Range: -8.1361
Max Act: 7.9486. Min Act: -0.1700
Data Index: 308983 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1361. Min Range: -8.1361
Max Act: 7.8861. Min Act: -0.1700
Data Index: 7678792 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1361. Min Range: -8.1361
Max Act: 7.8236. Min Act: -0.1700
Data Index: 7852439 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1361. Min Range: -8.1361
Max Act: 7.8236. Min Act: -0.1700
Data Index: 5606035 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1361. Min Range: -8.1361
Max Act: 7.8236. Min Act: -0.1700
Data Index: 898293 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1361. Min Range: -8.1361
Max Act: 7.8236. Min Act: -0.1700
Data Index: 4904893 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1361. Min Range: -8.1361
Max Act: 7.7611. Min Act: -0.1700
Data Index: 8448504 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1361. Min Range: -8.1361
Max Act: 7.7611. Min Act: -0.1700
Data Index: 1782588 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1361. Min Range: -8.1361
Max Act: 7.6986. Min Act: -0.1700
Data Index: 3697504 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1361. Min Range: -8.1361
Max Act: 7.7611. Min Act: -0.1700
Data Index: 7010647 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1361. Min Range: -8.1361
Max Act: 7.6986. Min Act: -0.1700
Data Index: 3506285 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1361. Min Range: -8.1361
Max Act: 7.6986. Min Act: -0.1700
Data Index: 5122435 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1361. Min Range: -8.1361
Max Act: 7.6986. Min Act: -0.1700
Data Index: 3258287 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1361. Min Range: -8.1361
Max Act: 7.6986. Min Act: -0.1700
Data Index: 2538150 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1361. Min Range: -8.1361
Max Act: 7.7611. Min Act: -0.1700
Data Index: 8336437 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1361. Min Range: -8.1361
Max Act: 7.6986. Min Act: -0.1700
Data Index: 4396610 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1361. Min Range: -8.1361
Max Act: 7.6361. Min Act: -0.1700
Data Index: 2960792 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1361. Min Range: -8.1361
Max Act: 7.6361. Min Act: -0.1700
Data Index: 5413355 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1361. Min Range: -8.1361
Max Act: 7.6361. Min Act: -0.1700
Data Index: 4895613 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19