Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2721 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0525. Min Range: -6.0525
Max Act: 6.0525. Min Act: -0.1700
Data Index: 72207 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0525. Min Range: -6.0525
Max Act: 5.9275. Min Act: -0.1700
Data Index: 5222634 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0525. Min Range: -6.0525
Max Act: 5.8338. Min Act: -0.1700
Data Index: 3525022 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0525. Min Range: -6.0525
Max Act: 5.7713. Min Act: -0.1700
Data Index: 6505121 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0525. Min Range: -6.0525
Max Act: 5.7088. Min Act: -0.1700
Data Index: 1175948 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0525. Min Range: -6.0525
Max Act: 5.6463. Min Act: -0.1700
Data Index: 2029290 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0525. Min Range: -6.0525
Max Act: 5.5838. Min Act: -0.1700
Data Index: 1066876 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0525. Min Range: -6.0525
Max Act: 5.5525. Min Act: -0.1700
Data Index: 1237538 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0525. Min Range: -6.0525
Max Act: 5.5213. Min Act: -0.1700
Data Index: 1556194 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0525. Min Range: -6.0525
Max Act: 5.4900. Min Act: -0.1700
Data Index: 2232729 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0525. Min Range: -6.0525
Max Act: 5.4900. Min Act: -0.1700
Data Index: 129432 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0525. Min Range: -6.0525
Max Act: 5.4900. Min Act: -0.1700
Data Index: 3776553 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0525. Min Range: -6.0525
Max Act: 5.4900. Min Act: -0.1700
Data Index: 3563086 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0525. Min Range: -6.0525
Max Act: 5.4588. Min Act: -0.1700
Data Index: 1621931 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0525. Min Range: -6.0525
Max Act: 5.4588. Min Act: -0.1700
Data Index: 6996863 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0525. Min Range: -6.0525
Max Act: 5.3963. Min Act: -0.1700
Data Index: 999179 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0525. Min Range: -6.0525
Max Act: 5.4275. Min Act: -0.1700
Data Index: 1168413 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0525. Min Range: -6.0525
Max Act: 5.4275. Min Act: -0.1700
Data Index: 1975501 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0525. Min Range: -6.0525
Max Act: 5.3650. Min Act: -0.1700
Data Index: 4643613 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0525. Min Range: -6.0525
Max Act: 5.3338. Min Act: -0.1700
Data Index: 2151084 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19