Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2029 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.8693. Min Act: -0.1700
Data Index: 8709826 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.6818. Min Act: -0.1700
Data Index: 8189484 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.5568. Min Act: -0.1700
Data Index: 8567189 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.5255. Min Act: -0.1700
Data Index: 1691232 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.4630. Min Act: -0.1700
Data Index: 2298913 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.4318. Min Act: -0.1700
Data Index: 8252345 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.4630. Min Act: -0.1700
Data Index: 8390381 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.4318. Min Act: -0.1700
Data Index: 2298919 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.4005. Min Act: -0.1700
Data Index: 717355 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.4005. Min Act: -0.1700
Data Index: 908034 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.4318. Min Act: -0.1700
Data Index: 7675943 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.3693. Min Act: -0.1700
Data Index: 3349265 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.3693. Min Act: -0.1700
Data Index: 7181923 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.3693. Min Act: -0.1700
Data Index: 5433462 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.3068. Min Act: -0.1700
Data Index: 2792184 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.2755. Min Act: -0.1700
Data Index: 4526430 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.2443. Min Act: -0.1700
Data Index: 1557980 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.2755. Min Act: -0.1700
Data Index: 6694056 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.2443. Min Act: -0.1700
Data Index: 3146069 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.2130. Min Act: -0.1700
Data Index: 3032272 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19