Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 896 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4183. Min Range: -6.4183
Max Act: 6.4183. Min Act: -0.1700
Data Index: 5329615 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4183. Min Range: -6.4183
Max Act: 5.9183. Min Act: -0.1700
Data Index: 8278276 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4183. Min Range: -6.4183
Max Act: 5.7621. Min Act: -0.1700
Data Index: 2256942 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4183. Min Range: -6.4183
Max Act: 5.6996. Min Act: -0.1700
Data Index: 4650068 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4183. Min Range: -6.4183
Max Act: 5.5433. Min Act: -0.1700
Data Index: 5239244 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4183. Min Range: -6.4183
Max Act: 5.5121. Min Act: -0.1700
Data Index: 8621746 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4183. Min Range: -6.4183
Max Act: 5.4183. Min Act: -0.1700
Data Index: 6641144 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4183. Min Range: -6.4183
Max Act: 5.4183. Min Act: -0.1700
Data Index: 1703279 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4183. Min Range: -6.4183
Max Act: 5.4183. Min Act: -0.1700
Data Index: 829484 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4183. Min Range: -6.4183
Max Act: 5.3558. Min Act: -0.1700
Data Index: 7082440 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4183. Min Range: -6.4183
Max Act: 5.3246. Min Act: -0.1700
Data Index: 5957283 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4183. Min Range: -6.4183
Max Act: 5.3246. Min Act: -0.1700
Data Index: 2997255 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4183. Min Range: -6.4183
Max Act: 5.3246. Min Act: -0.1700
Data Index: 533562 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4183. Min Range: -6.4183
Max Act: 5.3246. Min Act: -0.1700
Data Index: 1447034 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4183. Min Range: -6.4183
Max Act: 5.2933. Min Act: -0.1700
Data Index: 6996932 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4183. Min Range: -6.4183
Max Act: 5.2933. Min Act: -0.1700
Data Index: 8434407 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4183. Min Range: -6.4183
Max Act: 5.2621. Min Act: -0.1700
Data Index: 1496541 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4183. Min Range: -6.4183
Max Act: 5.2621. Min Act: -0.1700
Data Index: 3543545 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4183. Min Range: -6.4183
Max Act: 5.2621. Min Act: -0.1700
Data Index: 587875 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4183. Min Range: -6.4183
Max Act: 5.2621. Min Act: -0.1700
Data Index: 4277743 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19