Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6326 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0525. Min Range: -8.0525
Max Act: 8.0525. Min Act: -0.1700
Data Index: 7910955 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0525. Min Range: -8.0525
Max Act: 7.7400. Min Act: -0.1700
Data Index: 7233852 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0525. Min Range: -8.0525
Max Act: 7.1463. Min Act: -0.1700
Data Index: 5512316 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0525. Min Range: -8.0525
Max Act: 6.9900. Min Act: -0.1700
Data Index: 3053724 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0525. Min Range: -8.0525
Max Act: 7.0213. Min Act: -0.1700
Data Index: 4774541 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0525. Min Range: -8.0525
Max Act: 6.9900. Min Act: -0.1700
Data Index: 5757166 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0525. Min Range: -8.0525
Max Act: 6.9900. Min Act: -0.1700
Data Index: 4494044 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0525. Min Range: -8.0525
Max Act: 6.9275. Min Act: -0.1700
Data Index: 8631163 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0525. Min Range: -8.0525
Max Act: 6.9275. Min Act: -0.1700
Data Index: 2858128 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0525. Min Range: -8.0525
Max Act: 6.8650. Min Act: -0.1700
Data Index: 7483000 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0525. Min Range: -8.0525
Max Act: 6.8650. Min Act: -0.1700
Data Index: 2716104 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0525. Min Range: -8.0525
Max Act: 6.8338. Min Act: -0.1700
Data Index: 1850646 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0525. Min Range: -8.0525
Max Act: 6.8338. Min Act: -0.1700
Data Index: 6828033 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0525. Min Range: -8.0525
Max Act: 6.8025. Min Act: -0.1700
Data Index: 4685828 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0525. Min Range: -8.0525
Max Act: 6.8338. Min Act: -0.1700
Data Index: 2591093 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0525. Min Range: -8.0525
Max Act: 6.7713. Min Act: -0.1700
Data Index: 2908936 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0525. Min Range: -8.0525
Max Act: 6.8025. Min Act: -0.1700
Data Index: 8293241 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0525. Min Range: -8.0525
Max Act: 6.8025. Min Act: -0.1700
Data Index: 1614089 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0525. Min Range: -8.0525
Max Act: 6.7713. Min Act: -0.1700
Data Index: 1568519 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0525. Min Range: -8.0525
Max Act: 6.7713. Min Act: -0.1700
Data Index: 6774031 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19