Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2528 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0893. Min Range: -4.0893
Max Act: 4.0893. Min Act: -0.1700
Data Index: 2762852 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0893. Min Range: -4.0893
Max Act: 4.0893. Min Act: -0.1700
Data Index: 8496678 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0893. Min Range: -4.0893
Max Act: 4.0580. Min Act: -0.1700
Data Index: 8504198 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0893. Min Range: -4.0893
Max Act: 4.0580. Min Act: -0.1700
Data Index: 437248 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0893. Min Range: -4.0893
Max Act: 4.0268. Min Act: -0.1700
Data Index: 5287539 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0893. Min Range: -4.0893
Max Act: 4.0268. Min Act: -0.1700
Data Index: 5861055 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0893. Min Range: -4.0893
Max Act: 4.0268. Min Act: -0.1700
Data Index: 8587528 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0893. Min Range: -4.0893
Max Act: 4.0268. Min Act: -0.1700
Data Index: 4741976 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0893. Min Range: -4.0893
Max Act: 3.9955. Min Act: -0.1700
Data Index: 547968 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0893. Min Range: -4.0893
Max Act: 3.9955. Min Act: -0.1700
Data Index: 1359839 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0893. Min Range: -4.0893
Max Act: 3.9955. Min Act: -0.1700
Data Index: 850673 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0893. Min Range: -4.0893
Max Act: 3.9955. Min Act: -0.1700
Data Index: 3485289 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0893. Min Range: -4.0893
Max Act: 3.9955. Min Act: -0.1700
Data Index: 1571629 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0893. Min Range: -4.0893
Max Act: 3.9955. Min Act: -0.1700
Data Index: 3359826 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0893. Min Range: -4.0893
Max Act: 3.9643. Min Act: -0.1700
Data Index: 3013541 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0893. Min Range: -4.0893
Max Act: 3.9330. Min Act: -0.1700
Data Index: 8677235 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0893. Min Range: -4.0893
Max Act: 3.9017. Min Act: -0.1700
Data Index: 2982688 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0893. Min Range: -4.0893
Max Act: 3.9017. Min Act: -0.1700
Data Index: 918386 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0893. Min Range: -4.0893
Max Act: 3.9330. Min Act: -0.1700
Data Index: 4920659 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0893. Min Range: -4.0893
Max Act: 3.8705. Min Act: -0.1700
Data Index: 4410556 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19