Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2638 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9481. Min Range: -6.9481
Max Act: 6.9481. Min Act: -0.1700
Data Index: 8552118 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9481. Min Range: -6.9481
Max Act: 6.6668. Min Act: -0.1700
Data Index: 4188897 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9481. Min Range: -6.9481
Max Act: 6.5731. Min Act: -0.1700
Data Index: 1286585 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9481. Min Range: -6.9481
Max Act: 6.4793. Min Act: -0.1700
Data Index: 8725410 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9481. Min Range: -6.9481
Max Act: 6.3856. Min Act: -0.1700
Data Index: 6013110 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9481. Min Range: -6.9481
Max Act: 6.3856. Min Act: -0.1700
Data Index: 4872324 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9481. Min Range: -6.9481
Max Act: 6.3543. Min Act: -0.1700
Data Index: 3177025 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9481. Min Range: -6.9481
Max Act: 6.3543. Min Act: -0.1700
Data Index: 5602576 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9481. Min Range: -6.9481
Max Act: 6.3231. Min Act: -0.1700
Data Index: 1849136 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9481. Min Range: -6.9481
Max Act: 6.3231. Min Act: -0.1700
Data Index: 6783594 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9481. Min Range: -6.9481
Max Act: 6.2918. Min Act: -0.1700
Data Index: 1388347 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9481. Min Range: -6.9481
Max Act: 6.2918. Min Act: -0.1700
Data Index: 3065320 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9481. Min Range: -6.9481
Max Act: 6.2293. Min Act: -0.1700
Data Index: 8084732 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9481. Min Range: -6.9481
Max Act: 6.2606. Min Act: -0.1700
Data Index: 8662411 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9481. Min Range: -6.9481
Max Act: 6.2606. Min Act: -0.1700
Data Index: 8193212 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9481. Min Range: -6.9481
Max Act: 6.2606. Min Act: -0.1700
Data Index: 723383 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9481. Min Range: -6.9481
Max Act: 6.2293. Min Act: -0.1700
Data Index: 2999410 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9481. Min Range: -6.9481
Max Act: 6.2293. Min Act: -0.1700
Data Index: 1521871 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9481. Min Range: -6.9481
Max Act: 6.2293. Min Act: -0.1700
Data Index: 100903 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9481. Min Range: -6.9481
Max Act: 6.1981. Min Act: -0.1700
Data Index: 2008363 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19