Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5286 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7576. Min Range: -5.7576
Max Act: 5.7576. Min Act: -0.1700
Data Index: 1043986 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7576. Min Range: -5.7576
Max Act: 5.4451. Min Act: -0.1700
Data Index: 76119 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7576. Min Range: -5.7576
Max Act: 5.4451. Min Act: -0.1700
Data Index: 8109112 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7576. Min Range: -5.7576
Max Act: 5.4138. Min Act: -0.1700
Data Index: 4423193 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7576. Min Range: -5.7576
Max Act: 5.2888. Min Act: -0.1700
Data Index: 5253780 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7576. Min Range: -5.7576
Max Act: 5.1951. Min Act: -0.1700
Data Index: 2161654 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7576. Min Range: -5.7576
Max Act: 5.1638. Min Act: -0.1700
Data Index: 4383533 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7576. Min Range: -5.7576
Max Act: 5.1951. Min Act: -0.1700
Data Index: 8784264 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7576. Min Range: -5.7576
Max Act: 5.1638. Min Act: -0.1700
Data Index: 3429961 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7576. Min Range: -5.7576
Max Act: 5.1638. Min Act: -0.1700
Data Index: 5411469 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7576. Min Range: -5.7576
Max Act: 5.1638. Min Act: -0.1700
Data Index: 905946 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7576. Min Range: -5.7576
Max Act: 5.1326. Min Act: -0.1700
Data Index: 1843181 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7576. Min Range: -5.7576
Max Act: 5.1326. Min Act: -0.1700
Data Index: 384326 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7576. Min Range: -5.7576
Max Act: 5.1013. Min Act: -0.1700
Data Index: 7304511 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7576. Min Range: -5.7576
Max Act: 5.0701. Min Act: -0.1700
Data Index: 3366030 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7576. Min Range: -5.7576
Max Act: 5.0701. Min Act: -0.1700
Data Index: 5405182 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7576. Min Range: -5.7576
Max Act: 5.0701. Min Act: -0.1700
Data Index: 2904039 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7576. Min Range: -5.7576
Max Act: 5.0388. Min Act: -0.1700
Data Index: 110495 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7576. Min Range: -5.7576
Max Act: 5.0701. Min Act: -0.1700
Data Index: 2601033 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7576. Min Range: -5.7576
Max Act: 5.0388. Min Act: -0.1700
Data Index: 4302067 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19