Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6149 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2696. Min Range: -6.2696
Max Act: 6.2696. Min Act: -0.1700
Data Index: 4947225 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2696. Min Range: -6.2696
Max Act: 5.9259. Min Act: -0.1700
Data Index: 8365761 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2696. Min Range: -6.2696
Max Act: 5.9571. Min Act: -0.1700
Data Index: 3557588 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2696. Min Range: -6.2696
Max Act: 5.9571. Min Act: -0.1700
Data Index: 1052430 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2696. Min Range: -6.2696
Max Act: 5.8946. Min Act: -0.1700
Data Index: 1936209 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2696. Min Range: -6.2696
Max Act: 5.8634. Min Act: -0.1700
Data Index: 1344123 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2696. Min Range: -6.2696
Max Act: 5.8634. Min Act: -0.1700
Data Index: 5552144 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2696. Min Range: -6.2696
Max Act: 5.8321. Min Act: -0.1700
Data Index: 5240557 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2696. Min Range: -6.2696
Max Act: 5.8634. Min Act: -0.1700
Data Index: 8364483 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2696. Min Range: -6.2696
Max Act: 5.8321. Min Act: -0.1700
Data Index: 8584753 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2696. Min Range: -6.2696
Max Act: 5.8321. Min Act: -0.1700
Data Index: 6886853 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2696. Min Range: -6.2696
Max Act: 5.8009. Min Act: -0.1700
Data Index: 5519602 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2696. Min Range: -6.2696
Max Act: 5.8009. Min Act: -0.1700
Data Index: 2451624 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2696. Min Range: -6.2696
Max Act: 5.7384. Min Act: -0.1700
Data Index: 6484064 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2696. Min Range: -6.2696
Max Act: 5.7071. Min Act: -0.1700
Data Index: 4503783 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2696. Min Range: -6.2696
Max Act: 5.7071. Min Act: -0.1700
Data Index: 1936204 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2696. Min Range: -6.2696
Max Act: 5.6759. Min Act: -0.1700
Data Index: 4661933 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2696. Min Range: -6.2696
Max Act: 5.7071. Min Act: -0.1700
Data Index: 4274857 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2696. Min Range: -6.2696
Max Act: 5.7071. Min Act: -0.1700
Data Index: 3489373 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2696. Min Range: -6.2696
Max Act: 5.7071. Min Act: -0.1700
Data Index: 5283288 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19