Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1866 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2420. Min Range: -5.2420
Max Act: 5.2420. Min Act: -0.1700
Data Index: 775420 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2420. Min Range: -5.2420
Max Act: 5.1483. Min Act: -0.1700
Data Index: 6442671 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2420. Min Range: -5.2420
Max Act: 5.0545. Min Act: -0.1700
Data Index: 4173 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2420. Min Range: -5.2420
Max Act: 4.9920. Min Act: -0.1700
Data Index: 6526062 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2420. Min Range: -5.2420
Max Act: 4.9920. Min Act: -0.1700
Data Index: 8830182 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2420. Min Range: -5.2420
Max Act: 4.9608. Min Act: -0.1700
Data Index: 6831709 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2420. Min Range: -5.2420
Max Act: 4.9295. Min Act: -0.1700
Data Index: 7804830 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2420. Min Range: -5.2420
Max Act: 4.8670. Min Act: -0.1700
Data Index: 4646225 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2420. Min Range: -5.2420
Max Act: 4.8983. Min Act: -0.1700
Data Index: 1597731 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2420. Min Range: -5.2420
Max Act: 4.8983. Min Act: -0.1700
Data Index: 8321666 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2420. Min Range: -5.2420
Max Act: 4.8670. Min Act: -0.1700
Data Index: 8162761 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2420. Min Range: -5.2420
Max Act: 4.8983. Min Act: -0.1700
Data Index: 2218474 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2420. Min Range: -5.2420
Max Act: 4.8358. Min Act: -0.1700
Data Index: 2156461 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2420. Min Range: -5.2420
Max Act: 4.8358. Min Act: -0.1700
Data Index: 3815997 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2420. Min Range: -5.2420
Max Act: 4.8045. Min Act: -0.1700
Data Index: 7167465 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2420. Min Range: -5.2420
Max Act: 4.8358. Min Act: -0.1700
Data Index: 4598756 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2420. Min Range: -5.2420
Max Act: 4.8045. Min Act: -0.1700
Data Index: 5517409 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2420. Min Range: -5.2420
Max Act: 4.8045. Min Act: -0.1700
Data Index: 4326540 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2420. Min Range: -5.2420
Max Act: 4.7733. Min Act: -0.1700
Data Index: 3745137 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2420. Min Range: -5.2420
Max Act: 4.7733. Min Act: -0.1700
Data Index: 1923657 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #19