Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 413 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7540. Min Range: -2.7540
Max Act: 2.7540. Min Act: -0.1700
Data Index: 1421843 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7540. Min Range: -2.7540
Max Act: 2.6740. Min Act: -0.1700
Data Index: 1572953 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7540. Min Range: -2.7540
Max Act: 2.6580. Min Act: -0.1700
Data Index: 1941543 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7540. Min Range: -2.7540
Max Act: 2.6098. Min Act: -0.1700
Data Index: 338412 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7540. Min Range: -2.7540
Max Act: 2.5937. Min Act: -0.1700
Data Index: 2749690 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7540. Min Range: -2.7540
Max Act: 2.5615. Min Act: -0.1700
Data Index: 4726028 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7540. Min Range: -2.7540
Max Act: 2.5453. Min Act: -0.1700
Data Index: 2652174 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7540. Min Range: -2.7540
Max Act: 2.5130. Min Act: -0.1700
Data Index: 2415922 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7540. Min Range: -2.7540
Max Act: 2.5130. Min Act: -0.1700
Data Index: 7284626 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7540. Min Range: -2.7540
Max Act: 2.5130. Min Act: -0.1700
Data Index: 3087221 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7540. Min Range: -2.7540
Max Act: 2.5130. Min Act: -0.1700
Data Index: 964827 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7540. Min Range: -2.7540
Max Act: 2.4968. Min Act: -0.1700
Data Index: 7308867 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7540. Min Range: -2.7540
Max Act: 2.4968. Min Act: -0.1700
Data Index: 5778153 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7540. Min Range: -2.7540
Max Act: 2.4968. Min Act: -0.1700
Data Index: 1320461 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7540. Min Range: -2.7540
Max Act: 2.4644. Min Act: -0.1700
Data Index: 6410209 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7540. Min Range: -2.7540
Max Act: 2.4644. Min Act: -0.1700
Data Index: 195387 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7540. Min Range: -2.7540
Max Act: 2.4644. Min Act: -0.1700
Data Index: 6883589 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7540. Min Range: -2.7540
Max Act: 2.4644. Min Act: -0.1700
Data Index: 5590940 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7540. Min Range: -2.7540
Max Act: 2.4644. Min Act: -0.1700
Data Index: 1018283 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7540. Min Range: -2.7540
Max Act: 2.4644. Min Act: -0.1700
Data Index: 5103218 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19