Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 560 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6432. Min Range: -3.6432
Max Act: 3.6432. Min Act: -0.1700
Data Index: 3878988 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6432. Min Range: -3.6432
Max Act: 3.3926. Min Act: -0.1700
Data Index: 2286407 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6432. Min Range: -3.6432
Max Act: 3.3769. Min Act: -0.1700
Data Index: 489950 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6432. Min Range: -3.6432
Max Act: 3.3612. Min Act: -0.1700
Data Index: 3878989 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6432. Min Range: -3.6432
Max Act: 3.3612. Min Act: -0.1700
Data Index: 4903899 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6432. Min Range: -3.6432
Max Act: 3.3455. Min Act: -0.1700
Data Index: 6713565 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6432. Min Range: -3.6432
Max Act: 3.3141. Min Act: -0.1700
Data Index: 2899359 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6432. Min Range: -3.6432
Max Act: 3.2985. Min Act: -0.1700
Data Index: 174063 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6432. Min Range: -3.6432
Max Act: 3.2670. Min Act: -0.1700
Data Index: 950049 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6432. Min Range: -3.6432
Max Act: 3.2670. Min Act: -0.1700
Data Index: 667776 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6432. Min Range: -3.6432
Max Act: 3.2356. Min Act: -0.1700
Data Index: 8069456 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6432. Min Range: -3.6432
Max Act: 3.2513. Min Act: -0.1700
Data Index: 5609593 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6432. Min Range: -3.6432
Max Act: 3.2356. Min Act: -0.1700
Data Index: 6217228 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6432. Min Range: -3.6432
Max Act: 3.2356. Min Act: -0.1700
Data Index: 1293569 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6432. Min Range: -3.6432
Max Act: 3.2199. Min Act: -0.1700
Data Index: 8372664 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6432. Min Range: -3.6432
Max Act: 3.2042. Min Act: -0.1700
Data Index: 5773996 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6432. Min Range: -3.6432
Max Act: 3.2199. Min Act: -0.1700
Data Index: 6542495 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6432. Min Range: -3.6432
Max Act: 3.1885. Min Act: -0.1700
Data Index: 1374539 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6432. Min Range: -3.6432
Max Act: 3.2199. Min Act: -0.1700
Data Index: 838980 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6432. Min Range: -3.6432
Max Act: 3.1885. Min Act: -0.1700
Data Index: 2787038 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19