Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1928 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3476. Min Range: -5.3476
Max Act: 5.3476. Min Act: -0.1700
Data Index: 1323162 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3476. Min Range: -5.3476
Max Act: 5.2539. Min Act: -0.1700
Data Index: 1138592 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3476. Min Range: -5.3476
Max Act: 5.1914. Min Act: -0.1700
Data Index: 2858756 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3476. Min Range: -5.3476
Max Act: 5.1601. Min Act: -0.1700
Data Index: 3242259 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3476. Min Range: -5.3476
Max Act: 5.1601. Min Act: -0.1700
Data Index: 8128269 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3476. Min Range: -5.3476
Max Act: 5.1601. Min Act: -0.1700
Data Index: 5536171 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3476. Min Range: -5.3476
Max Act: 5.1289. Min Act: -0.1700
Data Index: 6233001 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3476. Min Range: -5.3476
Max Act: 5.1289. Min Act: -0.1700
Data Index: 706258 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3476. Min Range: -5.3476
Max Act: 5.1289. Min Act: -0.1700
Data Index: 8035883 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3476. Min Range: -5.3476
Max Act: 5.0976. Min Act: -0.1700
Data Index: 2708500 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3476. Min Range: -5.3476
Max Act: 5.0976. Min Act: -0.1700
Data Index: 7726414 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3476. Min Range: -5.3476
Max Act: 5.0976. Min Act: -0.1700
Data Index: 8713358 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3476. Min Range: -5.3476
Max Act: 5.0664. Min Act: -0.1700
Data Index: 5470799 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3476. Min Range: -5.3476
Max Act: 5.0664. Min Act: -0.1700
Data Index: 8205342 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3476. Min Range: -5.3476
Max Act: 5.0664. Min Act: -0.1700
Data Index: 6923644 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3476. Min Range: -5.3476
Max Act: 5.0351. Min Act: -0.1700
Data Index: 8495627 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3476. Min Range: -5.3476
Max Act: 5.0351. Min Act: -0.1700
Data Index: 2430658 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3476. Min Range: -5.3476
Max Act: 5.0351. Min Act: -0.1700
Data Index: 8197681 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3476. Min Range: -5.3476
Max Act: 5.0351. Min Act: -0.1700
Data Index: 763428 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3476. Min Range: -5.3476
Max Act: 5.0351. Min Act: -0.1700
Data Index: 7057802 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19