Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3241 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9689. Min Range: -3.9689
Max Act: 3.9689. Min Act: -0.1700
Data Index: 679611 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9689. Min Range: -3.9689
Max Act: 3.9377. Min Act: -0.1700
Data Index: 2499651 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9689. Min Range: -3.9689
Max Act: 3.9064. Min Act: -0.1700
Data Index: 2200610 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9689. Min Range: -3.9689
Max Act: 3.9064. Min Act: -0.1700
Data Index: 1783654 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9689. Min Range: -3.9689
Max Act: 3.8751. Min Act: -0.1700
Data Index: 1653069 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9689. Min Range: -3.9689
Max Act: 3.8751. Min Act: -0.1700
Data Index: 7860717 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9689. Min Range: -3.9689
Max Act: 3.8751. Min Act: -0.1700
Data Index: 6285603 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9689. Min Range: -3.9689
Max Act: 3.8439. Min Act: -0.1700
Data Index: 5585493 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9689. Min Range: -3.9689
Max Act: 3.8751. Min Act: -0.1700
Data Index: 5513075 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9689. Min Range: -3.9689
Max Act: 3.8751. Min Act: -0.1700
Data Index: 1552124 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9689. Min Range: -3.9689
Max Act: 3.8751. Min Act: -0.1700
Data Index: 4551817 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9689. Min Range: -3.9689
Max Act: 3.8439. Min Act: -0.1700
Data Index: 663333 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9689. Min Range: -3.9689
Max Act: 3.8439. Min Act: -0.1700
Data Index: 114352 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9689. Min Range: -3.9689
Max Act: 3.8439. Min Act: -0.1700
Data Index: 1131852 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9689. Min Range: -3.9689
Max Act: 3.8439. Min Act: -0.1700
Data Index: 1096266 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9689. Min Range: -3.9689
Max Act: 3.8439. Min Act: -0.1700
Data Index: 1026063 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9689. Min Range: -3.9689
Max Act: 3.8439. Min Act: -0.1700
Data Index: 3114052 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9689. Min Range: -3.9689
Max Act: 3.8126. Min Act: -0.1700
Data Index: 514341 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9689. Min Range: -3.9689
Max Act: 3.8126. Min Act: -0.1700
Data Index: 2315461 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9689. Min Range: -3.9689
Max Act: 3.8126. Min Act: -0.1700
Data Index: 2382574 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19