Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3503 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.4793. Min Act: -0.1700
Data Index: 1872993 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.4481. Min Act: -0.1700
Data Index: 7500456 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.3856. Min Act: -0.1700
Data Index: 2771535 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.3543. Min Act: -0.1700
Data Index: 2154753 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.3231. Min Act: -0.1700
Data Index: 7808473 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.2606. Min Act: -0.1700
Data Index: 7646613 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.2606. Min Act: -0.1700
Data Index: 5438004 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.2293. Min Act: -0.1700
Data Index: 2026241 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.1668. Min Act: -0.1700
Data Index: 8592920 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.1356. Min Act: -0.1700
Data Index: 8140202 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.1356. Min Act: -0.1700
Data Index: 390065 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.0731. Min Act: -0.1700
Data Index: 2243887 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.0418. Min Act: -0.1700
Data Index: 1310310 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.0418. Min Act: -0.1700
Data Index: 6489160 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.0418. Min Act: -0.1700
Data Index: 8639490 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.0106. Min Act: -0.1700
Data Index: 7391506 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.0418. Min Act: -0.1700
Data Index: 290679 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.0106. Min Act: -0.1700
Data Index: 862519 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.0106. Min Act: -0.1700
Data Index: 2160775 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.0106. Min Act: -0.1700
Data Index: 4713772 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #19