Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3353 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9028. Min Range: -6.9028
Max Act: 6.9028. Min Act: -0.1700
Data Index: 8050877 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9028. Min Range: -6.9028
Max Act: 6.8090. Min Act: -0.1700
Data Index: 3222946 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9028. Min Range: -6.9028
Max Act: 6.8403. Min Act: -0.1700
Data Index: 3702237 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9028. Min Range: -6.9028
Max Act: 6.7778. Min Act: -0.1700
Data Index: 3187004 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9028. Min Range: -6.9028
Max Act: 6.8090. Min Act: -0.1700
Data Index: 3076032 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9028. Min Range: -6.9028
Max Act: 6.7778. Min Act: -0.1700
Data Index: 5644530 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9028. Min Range: -6.9028
Max Act: 6.7778. Min Act: -0.1700
Data Index: 5387327 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9028. Min Range: -6.9028
Max Act: 6.7465. Min Act: -0.1700
Data Index: 2049399 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9028. Min Range: -6.9028
Max Act: 6.7153. Min Act: -0.1700
Data Index: 1212614 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9028. Min Range: -6.9028
Max Act: 6.7465. Min Act: -0.1700
Data Index: 1457699 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9028. Min Range: -6.9028
Max Act: 6.7465. Min Act: -0.1700
Data Index: 6835527 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9028. Min Range: -6.9028
Max Act: 6.7153. Min Act: -0.1700
Data Index: 2692543 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9028. Min Range: -6.9028
Max Act: 6.7153. Min Act: -0.1700
Data Index: 6511583 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9028. Min Range: -6.9028
Max Act: 6.7153. Min Act: -0.1700
Data Index: 491635 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9028. Min Range: -6.9028
Max Act: 6.6840. Min Act: -0.1700
Data Index: 7654326 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9028. Min Range: -6.9028
Max Act: 6.7153. Min Act: -0.1700
Data Index: 1112645 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9028. Min Range: -6.9028
Max Act: 6.6840. Min Act: -0.1700
Data Index: 447132 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9028. Min Range: -6.9028
Max Act: 6.6840. Min Act: -0.1700
Data Index: 6570753 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9028. Min Range: -6.9028
Max Act: 6.6840. Min Act: -0.1700
Data Index: 4728513 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9028. Min Range: -6.9028
Max Act: 6.6840. Min Act: -0.1700
Data Index: 5226853 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19