Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1668 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3920. Min Range: -9.3920
Max Act: 9.3920. Min Act: -0.1700
Data Index: 3227838 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3920. Min Range: -9.3920
Max Act: 9.3920. Min Act: -0.1700
Data Index: 3227845 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3920. Min Range: -9.3920
Max Act: 9.3295. Min Act: -0.1700
Data Index: 1090030 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3920. Min Range: -9.3920
Max Act: 8.9545. Min Act: -0.1700
Data Index: 5376819 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3920. Min Range: -9.3920
Max Act: 8.9545. Min Act: -0.1700
Data Index: 3227844 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3920. Min Range: -9.3920
Max Act: 8.8295. Min Act: -0.1700
Data Index: 5667674 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3920. Min Range: -9.3920
Max Act: 8.7670. Min Act: -0.1700
Data Index: 1090022 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3920. Min Range: -9.3920
Max Act: 8.7045. Min Act: -0.1700
Data Index: 1774042 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3920. Min Range: -9.3920
Max Act: 8.6420. Min Act: -0.1700
Data Index: 8014817 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3920. Min Range: -9.3920
Max Act: 8.6420. Min Act: -0.1700
Data Index: 2372155 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3920. Min Range: -9.3920
Max Act: 8.5170. Min Act: -0.1700
Data Index: 3955202 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3920. Min Range: -9.3920
Max Act: 8.5170. Min Act: -0.1700
Data Index: 946253 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3920. Min Range: -9.3920
Max Act: 8.4545. Min Act: -0.1700
Data Index: 2381205 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3920. Min Range: -9.3920
Max Act: 8.3920. Min Act: -0.1700
Data Index: 810511 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3920. Min Range: -9.3920
Max Act: 8.3295. Min Act: -0.1700
Data Index: 1090028 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3920. Min Range: -9.3920
Max Act: 8.3920. Min Act: -0.1700
Data Index: 592183 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3920. Min Range: -9.3920
Max Act: 8.2670. Min Act: -0.1700
Data Index: 646329 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3920. Min Range: -9.3920
Max Act: 8.3295. Min Act: -0.1700
Data Index: 1090021 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3920. Min Range: -9.3920
Max Act: 8.2670. Min Act: -0.1700
Data Index: 6830437 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3920. Min Range: -9.3920
Max Act: 8.3295. Min Act: -0.1700
Data Index: 1331374 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19