Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5356 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7380. Min Range: -6.7380
Max Act: 6.7380. Min Act: -0.1700
Data Index: 4242582 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7380. Min Range: -6.7380
Max Act: 6.6443. Min Act: -0.1700
Data Index: 4242585 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7380. Min Range: -6.7380
Max Act: 6.3630. Min Act: -0.1700
Data Index: 3296751 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7380. Min Range: -6.7380
Max Act: 6.3005. Min Act: -0.1700
Data Index: 1099476 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7380. Min Range: -6.7380
Max Act: 6.3005. Min Act: -0.1700
Data Index: 6485486 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7380. Min Range: -6.7380
Max Act: 6.2693. Min Act: -0.1700
Data Index: 4461114 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7380. Min Range: -6.7380
Max Act: 6.2068. Min Act: -0.1700
Data Index: 334855 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7380. Min Range: -6.7380
Max Act: 6.2068. Min Act: -0.1700
Data Index: 8654558 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7380. Min Range: -6.7380
Max Act: 6.1755. Min Act: -0.1700
Data Index: 7814555 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7380. Min Range: -6.7380
Max Act: 6.0818. Min Act: -0.1700
Data Index: 4180576 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7380. Min Range: -6.7380
Max Act: 6.0818. Min Act: -0.1700
Data Index: 169228 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7380. Min Range: -6.7380
Max Act: 6.0818. Min Act: -0.1700
Data Index: 5957862 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7380. Min Range: -6.7380
Max Act: 6.0505. Min Act: -0.1700
Data Index: 3330009 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7380. Min Range: -6.7380
Max Act: 6.0505. Min Act: -0.1700
Data Index: 3885984 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7380. Min Range: -6.7380
Max Act: 6.0505. Min Act: -0.1700
Data Index: 3968270 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7380. Min Range: -6.7380
Max Act: 6.0193. Min Act: -0.1700
Data Index: 1876223 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7380. Min Range: -6.7380
Max Act: 6.0193. Min Act: -0.1700
Data Index: 7280753 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7380. Min Range: -6.7380
Max Act: 5.9880. Min Act: -0.1700
Data Index: 3809682 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7380. Min Range: -6.7380
Max Act: 5.9880. Min Act: -0.1700
Data Index: 7770435 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7380. Min Range: -6.7380
Max Act: 5.9568. Min Act: -0.1700
Data Index: 2228673 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19