Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3532 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5763. Min Range: -5.5763
Max Act: 5.5763. Min Act: -0.1700
Data Index: 6698751 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5763. Min Range: -5.5763
Max Act: 5.5138. Min Act: -0.1700
Data Index: 3102055 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5763. Min Range: -5.5763
Max Act: 5.3575. Min Act: -0.1700
Data Index: 1626647 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5763. Min Range: -5.5763
Max Act: 5.3263. Min Act: -0.1700
Data Index: 1965168 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5763. Min Range: -5.5763
Max Act: 5.2950. Min Act: -0.1700
Data Index: 6527117 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5763. Min Range: -5.5763
Max Act: 5.2325. Min Act: -0.1700
Data Index: 3162511 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5763. Min Range: -5.5763
Max Act: 5.2013. Min Act: -0.1700
Data Index: 6378374 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5763. Min Range: -5.5763
Max Act: 5.1700. Min Act: -0.1700
Data Index: 3811557 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5763. Min Range: -5.5763
Max Act: 5.2013. Min Act: -0.1700
Data Index: 1653558 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5763. Min Range: -5.5763
Max Act: 5.1700. Min Act: -0.1700
Data Index: 560117 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5763. Min Range: -5.5763
Max Act: 5.1700. Min Act: -0.1700
Data Index: 3837531 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5763. Min Range: -5.5763
Max Act: 5.1075. Min Act: -0.1700
Data Index: 4503740 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5763. Min Range: -5.5763
Max Act: 5.1075. Min Act: -0.1700
Data Index: 4597760 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5763. Min Range: -5.5763
Max Act: 5.1075. Min Act: -0.1700
Data Index: 2143851 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5763. Min Range: -5.5763
Max Act: 5.1075. Min Act: -0.1700
Data Index: 1977982 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5763. Min Range: -5.5763
Max Act: 5.1075. Min Act: -0.1700
Data Index: 5489395 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5763. Min Range: -5.5763
Max Act: 5.0763. Min Act: -0.1700
Data Index: 69763 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5763. Min Range: -5.5763
Max Act: 5.0763. Min Act: -0.1700
Data Index: 1962187 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5763. Min Range: -5.5763
Max Act: 5.0763. Min Act: -0.1700
Data Index: 343196 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5763. Min Range: -5.5763
Max Act: 5.0763. Min Act: -0.1700
Data Index: 5756735 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19