Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 330 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7750. Min Range: -2.7750
Max Act: 2.7750. Min Act: -0.1700
Data Index: 4464747 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7750. Min Range: -2.7750
Max Act: 2.7750. Min Act: -0.1700
Data Index: 6262633 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7750. Min Range: -2.7750
Max Act: 2.7271. Min Act: -0.1700
Data Index: 8558258 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7750. Min Range: -2.7750
Max Act: 2.6631. Min Act: -0.1700
Data Index: 3247750 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7750. Min Range: -2.7750
Max Act: 2.6631. Min Act: -0.1700
Data Index: 2413398 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7750. Min Range: -2.7750
Max Act: 2.6631. Min Act: -0.1700
Data Index: 1402419 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7750. Min Range: -2.7750
Max Act: 2.6631. Min Act: -0.1700
Data Index: 4831050 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7750. Min Range: -2.7750
Max Act: 2.6631. Min Act: -0.1700
Data Index: 5814203 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7750. Min Range: -2.7750
Max Act: 2.6470. Min Act: -0.1700
Data Index: 5482890 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7750. Min Range: -2.7750
Max Act: 2.6310. Min Act: -0.1700
Data Index: 1033279 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7750. Min Range: -2.7750
Max Act: 2.6310. Min Act: -0.1700
Data Index: 2591414 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7750. Min Range: -2.7750
Max Act: 2.6310. Min Act: -0.1700
Data Index: 8266980 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7750. Min Range: -2.7750
Max Act: 2.6149. Min Act: -0.1700
Data Index: 7369907 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7750. Min Range: -2.7750
Max Act: 2.6149. Min Act: -0.1700
Data Index: 6988260 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7750. Min Range: -2.7750
Max Act: 2.6149. Min Act: -0.1700
Data Index: 3517456 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7750. Min Range: -2.7750
Max Act: 2.5988. Min Act: -0.1700
Data Index: 3146396 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7750. Min Range: -2.7750
Max Act: 2.5988. Min Act: -0.1700
Data Index: 105447 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7750. Min Range: -2.7750
Max Act: 2.5988. Min Act: -0.1700
Data Index: 4561442 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7750. Min Range: -2.7750
Max Act: 2.5988. Min Act: -0.1700
Data Index: 6122357 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7750. Min Range: -2.7750
Max Act: 2.5988. Min Act: -0.1700
Data Index: 194746 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19