Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6102 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.7648. Min Act: -0.1700
Data Index: 772500 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.7335. Min Act: -0.1700
Data Index: 8315856 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.6710. Min Act: -0.1700
Data Index: 5063283 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.6710. Min Act: -0.1700
Data Index: 4565610 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.7023. Min Act: -0.1700
Data Index: 2144791 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.6398. Min Act: -0.1700
Data Index: 718840 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.5460. Min Act: -0.1700
Data Index: 4137523 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.5148. Min Act: -0.1700
Data Index: 681946 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.4523. Min Act: -0.1700
Data Index: 2287083 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.4523. Min Act: -0.1700
Data Index: 3281244 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.3898. Min Act: -0.1700
Data Index: 3604165 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.3585. Min Act: -0.1700
Data Index: 8413180 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.3273. Min Act: -0.1700
Data Index: 6388889 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.3273. Min Act: -0.1700
Data Index: 4554087 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.2960. Min Act: -0.1700
Data Index: 1749667 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.2960. Min Act: -0.1700
Data Index: 3937645 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.2648. Min Act: -0.1700
Data Index: 4256746 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.2960. Min Act: -0.1700
Data Index: 4309833 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.2335. Min Act: -0.1700
Data Index: 1576269 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.2648. Min Act: -0.1700
Data Index: 4966175 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19