Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3532 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4686. Min Range: -7.4686
Max Act: 7.4686. Min Act: -0.1700
Data Index: 6814200 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4686. Min Range: -7.4686
Max Act: 6.9373. Min Act: -0.1700
Data Index: 3947574 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4686. Min Range: -7.4686
Max Act: 6.8123. Min Act: -0.1700
Data Index: 6804943 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4686. Min Range: -7.4686
Max Act: 6.6561. Min Act: -0.1700
Data Index: 7310739 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4686. Min Range: -7.4686
Max Act: 6.6561. Min Act: -0.1700
Data Index: 3098740 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4686. Min Range: -7.4686
Max Act: 6.6248. Min Act: -0.1700
Data Index: 8011572 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4686. Min Range: -7.4686
Max Act: 6.6248. Min Act: -0.1700
Data Index: 992498 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4686. Min Range: -7.4686
Max Act: 6.5936. Min Act: -0.1700
Data Index: 6359017 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4686. Min Range: -7.4686
Max Act: 6.5936. Min Act: -0.1700
Data Index: 3901915 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4686. Min Range: -7.4686
Max Act: 6.5311. Min Act: -0.1700
Data Index: 6570024 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4686. Min Range: -7.4686
Max Act: 6.5311. Min Act: -0.1700
Data Index: 459438 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4686. Min Range: -7.4686
Max Act: 6.5311. Min Act: -0.1700
Data Index: 7969114 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4686. Min Range: -7.4686
Max Act: 6.4998. Min Act: -0.1700
Data Index: 5818908 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4686. Min Range: -7.4686
Max Act: 6.4998. Min Act: -0.1700
Data Index: 7109260 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4686. Min Range: -7.4686
Max Act: 6.4998. Min Act: -0.1700
Data Index: 7630916 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4686. Min Range: -7.4686
Max Act: 6.4998. Min Act: -0.1700
Data Index: 5579874 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4686. Min Range: -7.4686
Max Act: 6.4686. Min Act: -0.1700
Data Index: 5867389 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4686. Min Range: -7.4686
Max Act: 6.4686. Min Act: -0.1700
Data Index: 6509058 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4686. Min Range: -7.4686
Max Act: 6.4373. Min Act: -0.1700
Data Index: 5672841 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4686. Min Range: -7.4686
Max Act: 6.4061. Min Act: -0.1700
Data Index: 1099881 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19