Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2448 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7352. Min Range: -3.7352
Max Act: 3.7352. Min Act: -0.1700
Data Index: 6027646 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7352. Min Range: -3.7352
Max Act: 3.6413. Min Act: -0.1700
Data Index: 189343 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7352. Min Range: -3.7352
Max Act: 3.6100. Min Act: -0.1700
Data Index: 2577904 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7352. Min Range: -3.7352
Max Act: 3.5318. Min Act: -0.1700
Data Index: 2577896 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7352. Min Range: -3.7352
Max Act: 3.4848. Min Act: -0.1700
Data Index: 6938478 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7352. Min Range: -3.7352
Max Act: 3.5004. Min Act: -0.1700
Data Index: 1777283 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7352. Min Range: -3.7352
Max Act: 3.4691. Min Act: -0.1700
Data Index: 7319747 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7352. Min Range: -3.7352
Max Act: 3.4534. Min Act: -0.1700
Data Index: 5461142 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7352. Min Range: -3.7352
Max Act: 3.4534. Min Act: -0.1700
Data Index: 619308 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7352. Min Range: -3.7352
Max Act: 3.4534. Min Act: -0.1700
Data Index: 761801 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7352. Min Range: -3.7352
Max Act: 3.4221. Min Act: -0.1700
Data Index: 3724816 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7352. Min Range: -3.7352
Max Act: 3.3907. Min Act: -0.1700
Data Index: 5848755 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7352. Min Range: -3.7352
Max Act: 3.3751. Min Act: -0.1700
Data Index: 1763645 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7352. Min Range: -3.7352
Max Act: 3.4064. Min Act: -0.1700
Data Index: 5913074 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7352. Min Range: -3.7352
Max Act: 3.3907. Min Act: -0.1700
Data Index: 8683321 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7352. Min Range: -3.7352
Max Act: 3.4064. Min Act: -0.1700
Data Index: 4852357 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7352. Min Range: -3.7352
Max Act: 3.3751. Min Act: -0.1700
Data Index: 8551495 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7352. Min Range: -3.7352
Max Act: 3.3907. Min Act: -0.1700
Data Index: 4075684 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7352. Min Range: -3.7352
Max Act: 3.3594. Min Act: -0.1700
Data Index: 6625509 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7352. Min Range: -3.7352
Max Act: 3.3751. Min Act: -0.1700
Data Index: 609076 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19