Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2197 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3893. Min Range: -6.3893
Max Act: 6.3893. Min Act: -0.1700
Data Index: 5423655 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3893. Min Range: -6.3893
Max Act: 6.2955. Min Act: -0.1700
Data Index: 1619439 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3893. Min Range: -6.3893
Max Act: 6.2643. Min Act: -0.1700
Data Index: 3325859 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3893. Min Range: -6.3893
Max Act: 6.1080. Min Act: -0.1700
Data Index: 878456 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3893. Min Range: -6.3893
Max Act: 5.9205. Min Act: -0.1700
Data Index: 5421744 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3893. Min Range: -6.3893
Max Act: 5.8893. Min Act: -0.1700
Data Index: 4797227 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3893. Min Range: -6.3893
Max Act: 5.8893. Min Act: -0.1700
Data Index: 662163 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3893. Min Range: -6.3893
Max Act: 5.8268. Min Act: -0.1700
Data Index: 1300277 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3893. Min Range: -6.3893
Max Act: 5.8580. Min Act: -0.1700
Data Index: 2999674 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3893. Min Range: -6.3893
Max Act: 5.8893. Min Act: -0.1700
Data Index: 4601734 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3893. Min Range: -6.3893
Max Act: 5.8268. Min Act: -0.1700
Data Index: 8477100 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3893. Min Range: -6.3893
Max Act: 5.8268. Min Act: -0.1700
Data Index: 4396250 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3893. Min Range: -6.3893
Max Act: 5.7955. Min Act: -0.1700
Data Index: 6887472 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3893. Min Range: -6.3893
Max Act: 5.7955. Min Act: -0.1700
Data Index: 4058629 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3893. Min Range: -6.3893
Max Act: 5.7955. Min Act: -0.1700
Data Index: 5363335 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3893. Min Range: -6.3893
Max Act: 5.7955. Min Act: -0.1700
Data Index: 1419241 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3893. Min Range: -6.3893
Max Act: 5.8268. Min Act: -0.1700
Data Index: 2474904 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3893. Min Range: -6.3893
Max Act: 5.7643. Min Act: -0.1700
Data Index: 5049779 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3893. Min Range: -6.3893
Max Act: 5.7330. Min Act: -0.1700
Data Index: 4683589 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3893. Min Range: -6.3893
Max Act: 5.7330. Min Act: -0.1700
Data Index: 751129 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19