Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1930 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5844. Min Range: -7.5844
Max Act: 7.5844. Min Act: -0.1700
Data Index: 7672626 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5844. Min Range: -7.5844
Max Act: 7.5844. Min Act: -0.1700
Data Index: 5835731 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5844. Min Range: -7.5844
Max Act: 7.5219. Min Act: -0.1700
Data Index: 8260155 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5844. Min Range: -7.5844
Max Act: 7.5219. Min Act: -0.1700
Data Index: 2111172 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5844. Min Range: -7.5844
Max Act: 7.4281. Min Act: -0.1700
Data Index: 650791 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5844. Min Range: -7.5844
Max Act: 7.3969. Min Act: -0.1700
Data Index: 8449167 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5844. Min Range: -7.5844
Max Act: 7.3969. Min Act: -0.1700
Data Index: 6961096 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5844. Min Range: -7.5844
Max Act: 7.3656. Min Act: -0.1700
Data Index: 4860840 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5844. Min Range: -7.5844
Max Act: 7.3344. Min Act: -0.1700
Data Index: 3691800 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5844. Min Range: -7.5844
Max Act: 7.3656. Min Act: -0.1700
Data Index: 147923 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5844. Min Range: -7.5844
Max Act: 7.3031. Min Act: -0.1700
Data Index: 3633147 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5844. Min Range: -7.5844
Max Act: 7.3031. Min Act: -0.1700
Data Index: 7461960 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5844. Min Range: -7.5844
Max Act: 7.3031. Min Act: -0.1700
Data Index: 6961097 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5844. Min Range: -7.5844
Max Act: 7.2719. Min Act: -0.1700
Data Index: 4615317 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5844. Min Range: -7.5844
Max Act: 7.2719. Min Act: -0.1700
Data Index: 1812835 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5844. Min Range: -7.5844
Max Act: 7.3031. Min Act: -0.1700
Data Index: 1889465 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5844. Min Range: -7.5844
Max Act: 7.2719. Min Act: -0.1700
Data Index: 6160123 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5844. Min Range: -7.5844
Max Act: 7.2719. Min Act: -0.1700
Data Index: 7699905 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5844. Min Range: -7.5844
Max Act: 7.2719. Min Act: -0.1700
Data Index: 4913816 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5844. Min Range: -7.5844
Max Act: 7.2719. Min Act: -0.1700
Data Index: 7461958 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19