Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2436 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5139. Min Range: -10.5139
Max Act: 10.5139. Min Act: -0.1700
Data Index: 7042173 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5139. Min Range: -10.5139
Max Act: 9.8889. Min Act: -0.1700
Data Index: 2678796 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5139. Min Range: -10.5139
Max Act: 9.8889. Min Act: -0.1700
Data Index: 5082474 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5139. Min Range: -10.5139
Max Act: 9.5764. Min Act: -0.1700
Data Index: 7968398 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5139. Min Range: -10.5139
Max Act: 9.5139. Min Act: -0.1700
Data Index: 6494278 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5139. Min Range: -10.5139
Max Act: 9.4514. Min Act: -0.1700
Data Index: 2195093 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5139. Min Range: -10.5139
Max Act: 9.3264. Min Act: -0.1700
Data Index: 4209274 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5139. Min Range: -10.5139
Max Act: 9.2639. Min Act: -0.1700
Data Index: 3920416 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5139. Min Range: -10.5139
Max Act: 9.2639. Min Act: -0.1700
Data Index: 949329 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5139. Min Range: -10.5139
Max Act: 9.2639. Min Act: -0.1700
Data Index: 4474328 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5139. Min Range: -10.5139
Max Act: 9.2014. Min Act: -0.1700
Data Index: 6708877 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5139. Min Range: -10.5139
Max Act: 9.2014. Min Act: -0.1700
Data Index: 5103835 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5139. Min Range: -10.5139
Max Act: 9.1389. Min Act: -0.1700
Data Index: 1620261 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5139. Min Range: -10.5139
Max Act: 9.0764. Min Act: -0.1700
Data Index: 5838827 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5139. Min Range: -10.5139
Max Act: 9.0764. Min Act: -0.1700
Data Index: 1885342 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5139. Min Range: -10.5139
Max Act: 9.0139. Min Act: -0.1700
Data Index: 8466493 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5139. Min Range: -10.5139
Max Act: 8.9514. Min Act: -0.1700
Data Index: 33841 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5139. Min Range: -10.5139
Max Act: 9.0139. Min Act: -0.1700
Data Index: 3884315 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5139. Min Range: -10.5139
Max Act: 8.9514. Min Act: -0.1700
Data Index: 8418053 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5139. Min Range: -10.5139
Max Act: 8.8889. Min Act: -0.1700
Data Index: 8372998 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19