Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5015 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5184. Min Range: -4.5184
Max Act: 4.5184. Min Act: -0.1700
Data Index: 1001950 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5184. Min Range: -4.5184
Max Act: 4.4559. Min Act: -0.1700
Data Index: 2562949 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5184. Min Range: -4.5184
Max Act: 4.4246. Min Act: -0.1700
Data Index: 1163910 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5184. Min Range: -4.5184
Max Act: 4.4246. Min Act: -0.1700
Data Index: 4902144 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5184. Min Range: -4.5184
Max Act: 4.3934. Min Act: -0.1700
Data Index: 4864759 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5184. Min Range: -4.5184
Max Act: 4.3309. Min Act: -0.1700
Data Index: 4981722 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5184. Min Range: -4.5184
Max Act: 4.3309. Min Act: -0.1700
Data Index: 1403894 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5184. Min Range: -4.5184
Max Act: 4.3309. Min Act: -0.1700
Data Index: 6922350 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5184. Min Range: -4.5184
Max Act: 4.2996. Min Act: -0.1700
Data Index: 8524514 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5184. Min Range: -4.5184
Max Act: 4.2996. Min Act: -0.1700
Data Index: 6959229 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5184. Min Range: -4.5184
Max Act: 4.2684. Min Act: -0.1700
Data Index: 2555275 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5184. Min Range: -4.5184
Max Act: 4.2684. Min Act: -0.1700
Data Index: 4201237 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5184. Min Range: -4.5184
Max Act: 4.2684. Min Act: -0.1700
Data Index: 5881646 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5184. Min Range: -4.5184
Max Act: 4.2684. Min Act: -0.1700
Data Index: 7997453 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5184. Min Range: -4.5184
Max Act: 4.2371. Min Act: -0.1700
Data Index: 4384089 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5184. Min Range: -4.5184
Max Act: 4.2371. Min Act: -0.1700
Data Index: 3859326 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5184. Min Range: -4.5184
Max Act: 4.2371. Min Act: -0.1700
Data Index: 997479 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5184. Min Range: -4.5184
Max Act: 4.2371. Min Act: -0.1700
Data Index: 5571721 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5184. Min Range: -4.5184
Max Act: 4.2058. Min Act: -0.1700
Data Index: 937187 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5184. Min Range: -4.5184
Max Act: 4.2058. Min Act: -0.1700
Data Index: 6517825 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19