Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4530 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9446. Min Range: -4.9446
Max Act: 4.9446. Min Act: -0.1700
Data Index: 8655982 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9446. Min Range: -4.9446
Max Act: 4.8196. Min Act: -0.1700
Data Index: 122416 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9446. Min Range: -4.9446
Max Act: 4.7884. Min Act: -0.1700
Data Index: 4403104 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9446. Min Range: -4.9446
Max Act: 4.7884. Min Act: -0.1700
Data Index: 4252162 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9446. Min Range: -4.9446
Max Act: 4.7884. Min Act: -0.1700
Data Index: 4344740 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9446. Min Range: -4.9446
Max Act: 4.7259. Min Act: -0.1700
Data Index: 801467 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9446. Min Range: -4.9446
Max Act: 4.7259. Min Act: -0.1700
Data Index: 1586267 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9446. Min Range: -4.9446
Max Act: 4.7259. Min Act: -0.1700
Data Index: 7109709 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9446. Min Range: -4.9446
Max Act: 4.7259. Min Act: -0.1700
Data Index: 3951355 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9446. Min Range: -4.9446
Max Act: 4.6634. Min Act: -0.1700
Data Index: 1597620 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9446. Min Range: -4.9446
Max Act: 4.6634. Min Act: -0.1700
Data Index: 1296440 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9446. Min Range: -4.9446
Max Act: 4.6634. Min Act: -0.1700
Data Index: 3396042 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9446. Min Range: -4.9446
Max Act: 4.6634. Min Act: -0.1700
Data Index: 5521615 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9446. Min Range: -4.9446
Max Act: 4.6321. Min Act: -0.1700
Data Index: 5060976 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9446. Min Range: -4.9446
Max Act: 4.6321. Min Act: -0.1700
Data Index: 8814390 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9446. Min Range: -4.9446
Max Act: 4.6009. Min Act: -0.1700
Data Index: 1597619 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9446. Min Range: -4.9446
Max Act: 4.6009. Min Act: -0.1700
Data Index: 3460778 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9446. Min Range: -4.9446
Max Act: 4.6009. Min Act: -0.1700
Data Index: 1665499 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9446. Min Range: -4.9446
Max Act: 4.6009. Min Act: -0.1700
Data Index: 2996544 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9446. Min Range: -4.9446
Max Act: 4.5696. Min Act: -0.1700
Data Index: 6680673 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19