Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5091 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8822. Min Range: -3.8822
Max Act: 3.8822. Min Act: -0.1700
Data Index: 4349425 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8822. Min Range: -3.8822
Max Act: 3.6946. Min Act: -0.1700
Data Index: 6691671 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8822. Min Range: -3.8822
Max Act: 3.6633. Min Act: -0.1700
Data Index: 195124 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8822. Min Range: -3.8822
Max Act: 3.6633. Min Act: -0.1700
Data Index: 4978287 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8822. Min Range: -3.8822
Max Act: 3.5851. Min Act: -0.1700
Data Index: 3318851 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8822. Min Range: -3.8822
Max Act: 3.6007. Min Act: -0.1700
Data Index: 6851199 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8822. Min Range: -3.8822
Max Act: 3.6007. Min Act: -0.1700
Data Index: 376521 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8822. Min Range: -3.8822
Max Act: 3.5537. Min Act: -0.1700
Data Index: 8326012 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8822. Min Range: -3.8822
Max Act: 3.5694. Min Act: -0.1700
Data Index: 6186519 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8822. Min Range: -3.8822
Max Act: 3.5381. Min Act: -0.1700
Data Index: 8326013 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8822. Min Range: -3.8822
Max Act: 3.4911. Min Act: -0.1700
Data Index: 150080 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8822. Min Range: -3.8822
Max Act: 3.4911. Min Act: -0.1700
Data Index: 7480272 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8822. Min Range: -3.8822
Max Act: 3.4598. Min Act: -0.1700
Data Index: 4681472 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8822. Min Range: -3.8822
Max Act: 3.4441. Min Act: -0.1700
Data Index: 7198749 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8822. Min Range: -3.8822
Max Act: 3.4598. Min Act: -0.1700
Data Index: 4327423 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8822. Min Range: -3.8822
Max Act: 3.4284. Min Act: -0.1700
Data Index: 3886335 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8822. Min Range: -3.8822
Max Act: 3.4284. Min Act: -0.1700
Data Index: 7294913 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8822. Min Range: -3.8822
Max Act: 3.4128. Min Act: -0.1700
Data Index: 6015068 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8822. Min Range: -3.8822
Max Act: 3.3814. Min Act: -0.1700
Data Index: 6015064 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8822. Min Range: -3.8822
Max Act: 3.3814. Min Act: -0.1700
Data Index: 3519337 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19