Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3516 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9573. Min Range: -5.9573
Max Act: 5.9573. Min Act: -0.1700
Data Index: 3539314 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9573. Min Range: -5.9573
Max Act: 5.9573. Min Act: -0.1700
Data Index: 3394112 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9573. Min Range: -5.9573
Max Act: 5.8948. Min Act: -0.1700
Data Index: 485142 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9573. Min Range: -5.9573
Max Act: 5.7698. Min Act: -0.1700
Data Index: 6617017 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9573. Min Range: -5.9573
Max Act: 5.7385. Min Act: -0.1700
Data Index: 2739816 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9573. Min Range: -5.9573
Max Act: 5.7385. Min Act: -0.1700
Data Index: 429342 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9573. Min Range: -5.9573
Max Act: 5.7385. Min Act: -0.1700
Data Index: 1562276 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9573. Min Range: -5.9573
Max Act: 5.7385. Min Act: -0.1700
Data Index: 4765868 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9573. Min Range: -5.9573
Max Act: 5.7073. Min Act: -0.1700
Data Index: 5297549 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9573. Min Range: -5.9573
Max Act: 5.7073. Min Act: -0.1700
Data Index: 7288324 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9573. Min Range: -5.9573
Max Act: 5.7073. Min Act: -0.1700
Data Index: 7259048 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9573. Min Range: -5.9573
Max Act: 5.6760. Min Act: -0.1700
Data Index: 5675470 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9573. Min Range: -5.9573
Max Act: 5.6760. Min Act: -0.1700
Data Index: 1844133 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9573. Min Range: -5.9573
Max Act: 5.6760. Min Act: -0.1700
Data Index: 7231983 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9573. Min Range: -5.9573
Max Act: 5.6135. Min Act: -0.1700
Data Index: 3396144 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9573. Min Range: -5.9573
Max Act: 5.6448. Min Act: -0.1700
Data Index: 8383932 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9573. Min Range: -5.9573
Max Act: 5.6448. Min Act: -0.1700
Data Index: 70842 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9573. Min Range: -5.9573
Max Act: 5.6448. Min Act: -0.1700
Data Index: 3303605 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9573. Min Range: -5.9573
Max Act: 5.6135. Min Act: -0.1700
Data Index: 725375 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9573. Min Range: -5.9573
Max Act: 5.6135. Min Act: -0.1700
Data Index: 420278 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19