Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3686 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2393. Min Range: -3.2393
Max Act: 3.2393. Min Act: -0.1700
Data Index: 4127538 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2393. Min Range: -3.2393
Max Act: 3.2393. Min Act: -0.1700
Data Index: 7930623 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2393. Min Range: -3.2393
Max Act: 3.1921. Min Act: -0.1700
Data Index: 1123094 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2393. Min Range: -3.2393
Max Act: 3.1764. Min Act: -0.1700
Data Index: 6451546 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2393. Min Range: -3.2393
Max Act: 3.1607. Min Act: -0.1700
Data Index: 5091492 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2393. Min Range: -3.2393
Max Act: 3.1607. Min Act: -0.1700
Data Index: 7160923 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2393. Min Range: -3.2393
Max Act: 3.1292. Min Act: -0.1700
Data Index: 7794222 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2393. Min Range: -3.2393
Max Act: 3.1292. Min Act: -0.1700
Data Index: 8241031 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2393. Min Range: -3.2393
Max Act: 3.1292. Min Act: -0.1700
Data Index: 8370645 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2393. Min Range: -3.2393
Max Act: 3.0504. Min Act: -0.1700
Data Index: 7621199 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2393. Min Range: -3.2393
Max Act: 3.0346. Min Act: -0.1700
Data Index: 4018684 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2393. Min Range: -3.2393
Max Act: 3.0504. Min Act: -0.1700
Data Index: 686287 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2393. Min Range: -3.2393
Max Act: 3.0346. Min Act: -0.1700
Data Index: 8162679 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2393. Min Range: -3.2393
Max Act: 3.0030. Min Act: -0.1700
Data Index: 2554098 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2393. Min Range: -3.2393
Max Act: 3.0188. Min Act: -0.1700
Data Index: 123649 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2393. Min Range: -3.2393
Max Act: 3.0030. Min Act: -0.1700
Data Index: 3455874 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2393. Min Range: -3.2393
Max Act: 2.9714. Min Act: -0.1700
Data Index: 8795612 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2393. Min Range: -3.2393
Max Act: 2.9714. Min Act: -0.1700
Data Index: 8826829 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2393. Min Range: -3.2393
Max Act: 2.9714. Min Act: -0.1700
Data Index: 771101 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2393. Min Range: -3.2393
Max Act: 2.9555. Min Act: -0.1700
Data Index: 7670122 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19