Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2393 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0344. Min Range: -7.0344
Max Act: 7.0344. Min Act: -0.1700
Data Index: 4962455 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0344. Min Range: -7.0344
Max Act: 6.7531. Min Act: -0.1700
Data Index: 4749280 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0344. Min Range: -7.0344
Max Act: 6.5656. Min Act: -0.1700
Data Index: 4036862 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0344. Min Range: -7.0344
Max Act: 6.5031. Min Act: -0.1700
Data Index: 5154042 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0344. Min Range: -7.0344
Max Act: 6.4406. Min Act: -0.1700
Data Index: 1320915 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0344. Min Range: -7.0344
Max Act: 6.3781. Min Act: -0.1700
Data Index: 3755707 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0344. Min Range: -7.0344
Max Act: 6.3469. Min Act: -0.1700
Data Index: 2489908 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0344. Min Range: -7.0344
Max Act: 6.3469. Min Act: -0.1700
Data Index: 2063291 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0344. Min Range: -7.0344
Max Act: 6.2844. Min Act: -0.1700
Data Index: 8449069 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0344. Min Range: -7.0344
Max Act: 6.2844. Min Act: -0.1700
Data Index: 6158389 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0344. Min Range: -7.0344
Max Act: 6.2844. Min Act: -0.1700
Data Index: 2804623 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0344. Min Range: -7.0344
Max Act: 6.2844. Min Act: -0.1700
Data Index: 483134 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0344. Min Range: -7.0344
Max Act: 6.2531. Min Act: -0.1700
Data Index: 8264589 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0344. Min Range: -7.0344
Max Act: 6.2219. Min Act: -0.1700
Data Index: 4972472 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0344. Min Range: -7.0344
Max Act: 6.2531. Min Act: -0.1700
Data Index: 5127892 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0344. Min Range: -7.0344
Max Act: 6.2531. Min Act: -0.1700
Data Index: 6471300 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0344. Min Range: -7.0344
Max Act: 6.2531. Min Act: -0.1700
Data Index: 5715901 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0344. Min Range: -7.0344
Max Act: 6.1906. Min Act: -0.1700
Data Index: 4299230 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0344. Min Range: -7.0344
Max Act: 6.1594. Min Act: -0.1700
Data Index: 5734985 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0344. Min Range: -7.0344
Max Act: 6.1594. Min Act: -0.1700
Data Index: 2936698 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19