Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3322 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8606. Min Range: -4.8606
Max Act: 4.8606. Min Act: -0.1700
Data Index: 971770 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8606. Min Range: -4.8606
Max Act: 4.7356. Min Act: -0.1700
Data Index: 8626270 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8606. Min Range: -4.8606
Max Act: 4.6419. Min Act: -0.1700
Data Index: 6807985 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8606. Min Range: -4.8606
Max Act: 4.6106. Min Act: -0.1700
Data Index: 422770 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8606. Min Range: -4.8606
Max Act: 4.6106. Min Act: -0.1700
Data Index: 7308155 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8606. Min Range: -4.8606
Max Act: 4.6106. Min Act: -0.1700
Data Index: 7415983 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8606. Min Range: -4.8606
Max Act: 4.5481. Min Act: -0.1700
Data Index: 7779658 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8606. Min Range: -4.8606
Max Act: 4.5481. Min Act: -0.1700
Data Index: 1314072 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8606. Min Range: -4.8606
Max Act: 4.5169. Min Act: -0.1700
Data Index: 7474014 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8606. Min Range: -4.8606
Max Act: 4.5481. Min Act: -0.1700
Data Index: 8100783 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8606. Min Range: -4.8606
Max Act: 4.5169. Min Act: -0.1700
Data Index: 4352038 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8606. Min Range: -4.8606
Max Act: 4.4856. Min Act: -0.1700
Data Index: 8545617 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8606. Min Range: -4.8606
Max Act: 4.4856. Min Act: -0.1700
Data Index: 2383281 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8606. Min Range: -4.8606
Max Act: 4.5169. Min Act: -0.1700
Data Index: 5199193 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8606. Min Range: -4.8606
Max Act: 4.4544. Min Act: -0.1700
Data Index: 5766331 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8606. Min Range: -4.8606
Max Act: 4.4544. Min Act: -0.1700
Data Index: 4892014 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8606. Min Range: -4.8606
Max Act: 4.4231. Min Act: -0.1700
Data Index: 2643409 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8606. Min Range: -4.8606
Max Act: 4.4231. Min Act: -0.1700
Data Index: 3890124 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8606. Min Range: -4.8606
Max Act: 4.4231. Min Act: -0.1700
Data Index: 8398458 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8606. Min Range: -4.8606
Max Act: 4.3919. Min Act: -0.1700
Data Index: 155125 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #19