Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3304 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6372. Min Range: -6.6372
Max Act: 6.6372. Min Act: -0.1700
Data Index: 1521746 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6372. Min Range: -6.6372
Max Act: 6.4810. Min Act: -0.1700
Data Index: 3389298 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6372. Min Range: -6.6372
Max Act: 6.3247. Min Act: -0.1700
Data Index: 148679 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6372. Min Range: -6.6372
Max Act: 6.3247. Min Act: -0.1700
Data Index: 2944259 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6372. Min Range: -6.6372
Max Act: 6.2622. Min Act: -0.1700
Data Index: 5147293 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6372. Min Range: -6.6372
Max Act: 6.2622. Min Act: -0.1700
Data Index: 1593862 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6372. Min Range: -6.6372
Max Act: 6.2935. Min Act: -0.1700
Data Index: 7799772 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6372. Min Range: -6.6372
Max Act: 6.2622. Min Act: -0.1700
Data Index: 7171534 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6372. Min Range: -6.6372
Max Act: 6.2622. Min Act: -0.1700
Data Index: 3303780 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6372. Min Range: -6.6372
Max Act: 6.2310. Min Act: -0.1700
Data Index: 2743849 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6372. Min Range: -6.6372
Max Act: 6.2310. Min Act: -0.1700
Data Index: 5729772 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6372. Min Range: -6.6372
Max Act: 6.1685. Min Act: -0.1700
Data Index: 4454997 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6372. Min Range: -6.6372
Max Act: 6.1997. Min Act: -0.1700
Data Index: 2151966 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6372. Min Range: -6.6372
Max Act: 6.1372. Min Act: -0.1700
Data Index: 5720420 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6372. Min Range: -6.6372
Max Act: 6.1685. Min Act: -0.1700
Data Index: 8286467 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6372. Min Range: -6.6372
Max Act: 6.1372. Min Act: -0.1700
Data Index: 8558871 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6372. Min Range: -6.6372
Max Act: 6.1372. Min Act: -0.1700
Data Index: 6603551 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6372. Min Range: -6.6372
Max Act: 6.1372. Min Act: -0.1700
Data Index: 407845 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6372. Min Range: -6.6372
Max Act: 6.0747. Min Act: -0.1700
Data Index: 1908272 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6372. Min Range: -6.6372
Max Act: 6.0747. Min Act: -0.1700
Data Index: 477848 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19