Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3072 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1592. Min Range: -6.1592
Max Act: 6.1592. Min Act: -0.1700
Data Index: 8350467 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1592. Min Range: -6.1592
Max Act: 6.1279. Min Act: -0.1700
Data Index: 2255024 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1592. Min Range: -6.1592
Max Act: 6.0967. Min Act: -0.1700
Data Index: 6916385 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1592. Min Range: -6.1592
Max Act: 6.1279. Min Act: -0.1700
Data Index: 7002511 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1592. Min Range: -6.1592
Max Act: 6.0967. Min Act: -0.1700
Data Index: 517073 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1592. Min Range: -6.1592
Max Act: 6.0967. Min Act: -0.1700
Data Index: 7631238 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1592. Min Range: -6.1592
Max Act: 6.0654. Min Act: -0.1700
Data Index: 6563389 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1592. Min Range: -6.1592
Max Act: 6.0342. Min Act: -0.1700
Data Index: 3164051 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1592. Min Range: -6.1592
Max Act: 6.0029. Min Act: -0.1700
Data Index: 4906499 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1592. Min Range: -6.1592
Max Act: 6.0029. Min Act: -0.1700
Data Index: 6553444 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1592. Min Range: -6.1592
Max Act: 5.9404. Min Act: -0.1700
Data Index: 3274378 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1592. Min Range: -6.1592
Max Act: 5.9404. Min Act: -0.1700
Data Index: 6563388 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1592. Min Range: -6.1592
Max Act: 5.9404. Min Act: -0.1700
Data Index: 564106 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1592. Min Range: -6.1592
Max Act: 5.9092. Min Act: -0.1700
Data Index: 5451647 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1592. Min Range: -6.1592
Max Act: 5.8467. Min Act: -0.1700
Data Index: 3496687 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1592. Min Range: -6.1592
Max Act: 5.8779. Min Act: -0.1700
Data Index: 8670871 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1592. Min Range: -6.1592
Max Act: 5.8779. Min Act: -0.1700
Data Index: 7754837 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1592. Min Range: -6.1592
Max Act: 5.8154. Min Act: -0.1700
Data Index: 309954 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1592. Min Range: -6.1592
Max Act: 5.7842. Min Act: -0.1700
Data Index: 7772758 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1592. Min Range: -6.1592
Max Act: 5.7842. Min Act: -0.1700
Data Index: 4695082 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19