Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4373 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1694. Min Range: -6.1694
Max Act: 6.1694. Min Act: -0.1700
Data Index: 4272981 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1694. Min Range: -6.1694
Max Act: 6.0444. Min Act: -0.1700
Data Index: 5647681 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.9819. Min Act: -0.1700
Data Index: 2472967 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.9506. Min Act: -0.1700
Data Index: 2518417 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.9194. Min Act: -0.1700
Data Index: 7670336 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.8256. Min Act: -0.1700
Data Index: 356853 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.8569. Min Act: -0.1700
Data Index: 6089399 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.8256. Min Act: -0.1700
Data Index: 1089977 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.8256. Min Act: -0.1700
Data Index: 292019 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.8256. Min Act: -0.1700
Data Index: 3149336 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.8256. Min Act: -0.1700
Data Index: 7678605 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.8256. Min Act: -0.1700
Data Index: 2917833 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.7944. Min Act: -0.1700
Data Index: 1974845 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.8256. Min Act: -0.1700
Data Index: 5647682 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.7944. Min Act: -0.1700
Data Index: 8333140 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.8256. Min Act: -0.1700
Data Index: 3078346 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.7631. Min Act: -0.1700
Data Index: 4603217 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.7631. Min Act: -0.1700
Data Index: 2617594 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.7631. Min Act: -0.1700
Data Index: 7797983 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1694. Min Range: -6.1694
Max Act: 5.7631. Min Act: -0.1700
Data Index: 8252342 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19