Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2668 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1552. Min Range: -5.1552
Max Act: 5.1552. Min Act: -0.1700
Data Index: 1305701 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1552. Min Range: -5.1552
Max Act: 4.9364. Min Act: -0.1700
Data Index: 8432453 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1552. Min Range: -5.1552
Max Act: 4.9989. Min Act: -0.1700
Data Index: 4063232 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1552. Min Range: -5.1552
Max Act: 4.9364. Min Act: -0.1700
Data Index: 8365043 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1552. Min Range: -5.1552
Max Act: 4.9364. Min Act: -0.1700
Data Index: 563062 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1552. Min Range: -5.1552
Max Act: 4.9052. Min Act: -0.1700
Data Index: 1241371 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1552. Min Range: -5.1552
Max Act: 4.8739. Min Act: -0.1700
Data Index: 1241378 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1552. Min Range: -5.1552
Max Act: 4.8427. Min Act: -0.1700
Data Index: 4865822 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1552. Min Range: -5.1552
Max Act: 4.8427. Min Act: -0.1700
Data Index: 3982976 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1552. Min Range: -5.1552
Max Act: 4.8427. Min Act: -0.1700
Data Index: 3756863 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1552. Min Range: -5.1552
Max Act: 4.8739. Min Act: -0.1700
Data Index: 2549951 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1552. Min Range: -5.1552
Max Act: 4.8114. Min Act: -0.1700
Data Index: 3902777 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1552. Min Range: -5.1552
Max Act: 4.8114. Min Act: -0.1700
Data Index: 6713288 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1552. Min Range: -5.1552
Max Act: 4.8114. Min Act: -0.1700
Data Index: 7022174 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1552. Min Range: -5.1552
Max Act: 4.8114. Min Act: -0.1700
Data Index: 4248980 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1552. Min Range: -5.1552
Max Act: 4.7802. Min Act: -0.1700
Data Index: 2989764 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1552. Min Range: -5.1552
Max Act: 4.7802. Min Act: -0.1700
Data Index: 3767034 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1552. Min Range: -5.1552
Max Act: 4.8114. Min Act: -0.1700
Data Index: 5493498 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1552. Min Range: -5.1552
Max Act: 4.8114. Min Act: -0.1700
Data Index: 376958 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1552. Min Range: -5.1552
Max Act: 4.7802. Min Act: -0.1700
Data Index: 1626801 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19