Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2292 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0893. Min Range: -6.0893
Max Act: 6.0893. Min Act: -0.1700
Data Index: 3175781 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0893. Min Range: -6.0893
Max Act: 6.0268. Min Act: -0.1700
Data Index: 3795424 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0893. Min Range: -6.0893
Max Act: 6.0268. Min Act: -0.1700
Data Index: 5656095 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0893. Min Range: -6.0893
Max Act: 6.0268. Min Act: -0.1700
Data Index: 8618120 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0893. Min Range: -6.0893
Max Act: 6.0268. Min Act: -0.1700
Data Index: 611597 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0893. Min Range: -6.0893
Max Act: 5.9956. Min Act: -0.1700
Data Index: 2828338 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0893. Min Range: -6.0893
Max Act: 5.9956. Min Act: -0.1700
Data Index: 7430101 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0893. Min Range: -6.0893
Max Act: 5.9643. Min Act: -0.1700
Data Index: 6832201 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0893. Min Range: -6.0893
Max Act: 5.9643. Min Act: -0.1700
Data Index: 7275355 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0893. Min Range: -6.0893
Max Act: 5.9331. Min Act: -0.1700
Data Index: 8392024 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0893. Min Range: -6.0893
Max Act: 5.9331. Min Act: -0.1700
Data Index: 1167881 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0893. Min Range: -6.0893
Max Act: 5.9018. Min Act: -0.1700
Data Index: 1792992 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0893. Min Range: -6.0893
Max Act: 5.9018. Min Act: -0.1700
Data Index: 2324504 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0893. Min Range: -6.0893
Max Act: 5.9018. Min Act: -0.1700
Data Index: 1233486 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0893. Min Range: -6.0893
Max Act: 5.9018. Min Act: -0.1700
Data Index: 7812423 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0893. Min Range: -6.0893
Max Act: 5.9018. Min Act: -0.1700
Data Index: 8212702 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0893. Min Range: -6.0893
Max Act: 5.9018. Min Act: -0.1700
Data Index: 5334155 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0893. Min Range: -6.0893
Max Act: 5.8706. Min Act: -0.1700
Data Index: 6799254 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0893. Min Range: -6.0893
Max Act: 5.8706. Min Act: -0.1700
Data Index: 7580550 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0893. Min Range: -6.0893
Max Act: 5.8706. Min Act: -0.1700
Data Index: 8614457 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19