Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5052 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0509. Min Range: -4.0509
Max Act: 4.0509. Min Act: -0.1700
Data Index: 8495727 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0509. Min Range: -4.0509
Max Act: 4.0509. Min Act: -0.1700
Data Index: 6955717 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0509. Min Range: -4.0509
Max Act: 4.0196. Min Act: -0.1700
Data Index: 1113198 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0509. Min Range: -4.0509
Max Act: 3.9884. Min Act: -0.1700
Data Index: 5675972 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0509. Min Range: -4.0509
Max Act: 3.9884. Min Act: -0.1700
Data Index: 6895664 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0509. Min Range: -4.0509
Max Act: 3.9571. Min Act: -0.1700
Data Index: 5769415 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0509. Min Range: -4.0509
Max Act: 3.9571. Min Act: -0.1700
Data Index: 4913054 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0509. Min Range: -4.0509
Max Act: 3.9259. Min Act: -0.1700
Data Index: 5655366 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0509. Min Range: -4.0509
Max Act: 3.8633. Min Act: -0.1700
Data Index: 2131606 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0509. Min Range: -4.0509
Max Act: 3.8946. Min Act: -0.1700
Data Index: 813585 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0509. Min Range: -4.0509
Max Act: 3.8633. Min Act: -0.1700
Data Index: 5675971 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0509. Min Range: -4.0509
Max Act: 3.8633. Min Act: -0.1700
Data Index: 3202686 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0509. Min Range: -4.0509
Max Act: 3.8321. Min Act: -0.1700
Data Index: 6446931 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0509. Min Range: -4.0509
Max Act: 3.8321. Min Act: -0.1700
Data Index: 5062694 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0509. Min Range: -4.0509
Max Act: 3.8321. Min Act: -0.1700
Data Index: 2865584 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0509. Min Range: -4.0509
Max Act: 3.8008. Min Act: -0.1700
Data Index: 642380 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0509. Min Range: -4.0509
Max Act: 3.7695. Min Act: -0.1700
Data Index: 2476599 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0509. Min Range: -4.0509
Max Act: 3.7695. Min Act: -0.1700
Data Index: 3832785 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0509. Min Range: -4.0509
Max Act: 3.7695. Min Act: -0.1700
Data Index: 4328979 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0509. Min Range: -4.0509
Max Act: 3.7695. Min Act: -0.1700
Data Index: 6165287 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19