Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1441 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2650. Min Range: -8.2650
Max Act: 8.2650. Min Act: -0.1700
Data Index: 6634601 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2650. Min Range: -8.2650
Max Act: 7.8900. Min Act: -0.1700
Data Index: 5099459 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2650. Min Range: -8.2650
Max Act: 7.8275. Min Act: -0.1700
Data Index: 7966919 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2650. Min Range: -8.2650
Max Act: 7.7963. Min Act: -0.1700
Data Index: 6639489 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2650. Min Range: -8.2650
Max Act: 7.7650. Min Act: -0.1700
Data Index: 2115884 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2650. Min Range: -8.2650
Max Act: 7.7963. Min Act: -0.1700
Data Index: 6265625 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2650. Min Range: -8.2650
Max Act: 7.8275. Min Act: -0.1700
Data Index: 6758337 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2650. Min Range: -8.2650
Max Act: 7.7338. Min Act: -0.1700
Data Index: 3687154 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2650. Min Range: -8.2650
Max Act: 7.6400. Min Act: -0.1700
Data Index: 396783 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2650. Min Range: -8.2650
Max Act: 7.6088. Min Act: -0.1700
Data Index: 788069 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2650. Min Range: -8.2650
Max Act: 7.5775. Min Act: -0.1700
Data Index: 640526 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2650. Min Range: -8.2650
Max Act: 7.4838. Min Act: -0.1700
Data Index: 6283038 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2650. Min Range: -8.2650
Max Act: 7.5150. Min Act: -0.1700
Data Index: 8666162 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2650. Min Range: -8.2650
Max Act: 7.4525. Min Act: -0.1700
Data Index: 4246553 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2650. Min Range: -8.2650
Max Act: 7.4525. Min Act: -0.1700
Data Index: 948944 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2650. Min Range: -8.2650
Max Act: 7.4525. Min Act: -0.1700
Data Index: 3779149 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2650. Min Range: -8.2650
Max Act: 7.4213. Min Act: -0.1700
Data Index: 7984761 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2650. Min Range: -8.2650
Max Act: 7.4213. Min Act: -0.1700
Data Index: 5178874 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2650. Min Range: -8.2650
Max Act: 7.4213. Min Act: -0.1700
Data Index: 8606712 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2650. Min Range: -8.2650
Max Act: 7.4213. Min Act: -0.1700
Data Index: 923572 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19