Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3180 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.4182. Min Act: -0.1700
Data Index: 1276155 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.2932. Min Act: -0.1700
Data Index: 3391877 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.2619. Min Act: -0.1700
Data Index: 2598727 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.2307. Min Act: -0.1700
Data Index: 6001957 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.1682. Min Act: -0.1700
Data Index: 8431755 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.1369. Min Act: -0.1700
Data Index: 8737165 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.0744. Min Act: -0.1700
Data Index: 5899064 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.0744. Min Act: -0.1700
Data Index: 723215 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.0744. Min Act: -0.1700
Data Index: 2101826 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.0432. Min Act: -0.1700
Data Index: 2905565 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.0119. Min Act: -0.1700
Data Index: 5922850 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.0119. Min Act: -0.1700
Data Index: 7549320 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4182. Min Range: -5.4182
Max Act: 4.9494. Min Act: -0.1700
Data Index: 1928680 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4182. Min Range: -5.4182
Max Act: 4.9807. Min Act: -0.1700
Data Index: 2091881 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4182. Min Range: -5.4182
Max Act: 4.9807. Min Act: -0.1700
Data Index: 2091880 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4182. Min Range: -5.4182
Max Act: 4.9494. Min Act: -0.1700
Data Index: 863614 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4182. Min Range: -5.4182
Max Act: 4.9182. Min Act: -0.1700
Data Index: 7251462 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4182. Min Range: -5.4182
Max Act: 4.9182. Min Act: -0.1700
Data Index: 7528504 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4182. Min Range: -5.4182
Max Act: 4.9182. Min Act: -0.1700
Data Index: 39822 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4182. Min Range: -5.4182
Max Act: 4.8557. Min Act: -0.1700
Data Index: 16273 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19