Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2921 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3528. Min Range: -7.3528
Max Act: 7.3528. Min Act: -0.1700
Data Index: 7438322 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3528. Min Range: -7.3528
Max Act: 7.2903. Min Act: -0.1700
Data Index: 6654932 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3528. Min Range: -7.3528
Max Act: 7.2278. Min Act: -0.1700
Data Index: 4639355 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3528. Min Range: -7.3528
Max Act: 7.1965. Min Act: -0.1700
Data Index: 8504613 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3528. Min Range: -7.3528
Max Act: 7.1653. Min Act: -0.1700
Data Index: 212597 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3528. Min Range: -7.3528
Max Act: 7.1653. Min Act: -0.1700
Data Index: 3107265 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3528. Min Range: -7.3528
Max Act: 7.1340. Min Act: -0.1700
Data Index: 2165933 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3528. Min Range: -7.3528
Max Act: 7.0090. Min Act: -0.1700
Data Index: 1570640 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3528. Min Range: -7.3528
Max Act: 6.9465. Min Act: -0.1700
Data Index: 6246120 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3528. Min Range: -7.3528
Max Act: 6.8840. Min Act: -0.1700
Data Index: 1163884 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3528. Min Range: -7.3528
Max Act: 6.8840. Min Act: -0.1700
Data Index: 2872489 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3528. Min Range: -7.3528
Max Act: 6.8528. Min Act: -0.1700
Data Index: 2587927 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3528. Min Range: -7.3528
Max Act: 6.8528. Min Act: -0.1700
Data Index: 4078862 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3528. Min Range: -7.3528
Max Act: 6.8215. Min Act: -0.1700
Data Index: 4956928 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3528. Min Range: -7.3528
Max Act: 6.8215. Min Act: -0.1700
Data Index: 8334266 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3528. Min Range: -7.3528
Max Act: 6.8215. Min Act: -0.1700
Data Index: 1327666 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3528. Min Range: -7.3528
Max Act: 6.7903. Min Act: -0.1700
Data Index: 3903468 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3528. Min Range: -7.3528
Max Act: 6.7590. Min Act: -0.1700
Data Index: 2747220 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3528. Min Range: -7.3528
Max Act: 6.7590. Min Act: -0.1700
Data Index: 7997700 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3528. Min Range: -7.3528
Max Act: 6.7590. Min Act: -0.1700
Data Index: 4966151 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19