Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 829 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0946. Min Range: -3.0946
Max Act: 3.0946. Min Act: -0.1700
Data Index: 5067135 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0946. Min Range: -3.0946
Max Act: 3.0315. Min Act: -0.1700
Data Index: 377167 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0946. Min Range: -3.0946
Max Act: 3.0631. Min Act: -0.1700
Data Index: 4763918 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0946. Min Range: -3.0946
Max Act: 3.0473. Min Act: -0.1700
Data Index: 5280380 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.9999. Min Act: -0.1700
Data Index: 8591595 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.9841. Min Act: -0.1700
Data Index: 5286001 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.9841. Min Act: -0.1700
Data Index: 1466277 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.9525. Min Act: -0.1700
Data Index: 131289 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.9683. Min Act: -0.1700
Data Index: 403135 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.9525. Min Act: -0.1700
Data Index: 3796993 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.9208. Min Act: -0.1700
Data Index: 5021781 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.9208. Min Act: -0.1700
Data Index: 6601676 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.9208. Min Act: -0.1700
Data Index: 1202298 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.9208. Min Act: -0.1700
Data Index: 419318 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.9050. Min Act: -0.1700
Data Index: 750850 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.9050. Min Act: -0.1700
Data Index: 3700375 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.9208. Min Act: -0.1700
Data Index: 4186026 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.9050. Min Act: -0.1700
Data Index: 5897142 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.9208. Min Act: -0.1700
Data Index: 7320801 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.8732. Min Act: -0.1700
Data Index: 5462456 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19