Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5982 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5560. Min Range: -5.5560
Max Act: 5.5560. Min Act: -0.1700
Data Index: 1449783 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5560. Min Range: -5.5560
Max Act: 5.3685. Min Act: -0.1700
Data Index: 2392285 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5560. Min Range: -5.5560
Max Act: 5.3685. Min Act: -0.1700
Data Index: 5641447 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5560. Min Range: -5.5560
Max Act: 5.2747. Min Act: -0.1700
Data Index: 1089332 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5560. Min Range: -5.5560
Max Act: 5.2435. Min Act: -0.1700
Data Index: 6843765 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5560. Min Range: -5.5560
Max Act: 5.2122. Min Act: -0.1700
Data Index: 4999918 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5560. Min Range: -5.5560
Max Act: 5.2122. Min Act: -0.1700
Data Index: 6438020 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5560. Min Range: -5.5560
Max Act: 5.2122. Min Act: -0.1700
Data Index: 7347759 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5560. Min Range: -5.5560
Max Act: 5.1810. Min Act: -0.1700
Data Index: 1331358 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5560. Min Range: -5.5560
Max Act: 5.1810. Min Act: -0.1700
Data Index: 831185 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5560. Min Range: -5.5560
Max Act: 5.1810. Min Act: -0.1700
Data Index: 2622344 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5560. Min Range: -5.5560
Max Act: 5.1497. Min Act: -0.1700
Data Index: 2162519 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5560. Min Range: -5.5560
Max Act: 5.1810. Min Act: -0.1700
Data Index: 7505889 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5560. Min Range: -5.5560
Max Act: 5.1185. Min Act: -0.1700
Data Index: 2474806 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5560. Min Range: -5.5560
Max Act: 5.1185. Min Act: -0.1700
Data Index: 154450 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5560. Min Range: -5.5560
Max Act: 5.1185. Min Act: -0.1700
Data Index: 67951 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5560. Min Range: -5.5560
Max Act: 5.1185. Min Act: -0.1700
Data Index: 4647253 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5560. Min Range: -5.5560
Max Act: 5.0872. Min Act: -0.1700
Data Index: 945314 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5560. Min Range: -5.5560
Max Act: 5.0872. Min Act: -0.1700
Data Index: 4607131 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5560. Min Range: -5.5560
Max Act: 5.0872. Min Act: -0.1700
Data Index: 1249950 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19