Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3369 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8104. Min Range: -7.8104
Max Act: 7.8104. Min Act: -0.1700
Data Index: 3232127 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8104. Min Range: -7.8104
Max Act: 7.7167. Min Act: -0.1700
Data Index: 2067358 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8104. Min Range: -7.8104
Max Act: 7.6229. Min Act: -0.1700
Data Index: 4570188 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8104. Min Range: -7.8104
Max Act: 7.5917. Min Act: -0.1700
Data Index: 4362941 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8104. Min Range: -7.8104
Max Act: 7.5917. Min Act: -0.1700
Data Index: 3005499 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8104. Min Range: -7.8104
Max Act: 7.4979. Min Act: -0.1700
Data Index: 1916606 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8104. Min Range: -7.8104
Max Act: 7.4979. Min Act: -0.1700
Data Index: 611278 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8104. Min Range: -7.8104
Max Act: 7.4354. Min Act: -0.1700
Data Index: 6221075 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8104. Min Range: -7.8104
Max Act: 7.3417. Min Act: -0.1700
Data Index: 2332547 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8104. Min Range: -7.8104
Max Act: 7.3104. Min Act: -0.1700
Data Index: 4132816 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8104. Min Range: -7.8104
Max Act: 7.3417. Min Act: -0.1700
Data Index: 1515801 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8104. Min Range: -7.8104
Max Act: 7.3104. Min Act: -0.1700
Data Index: 538723 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8104. Min Range: -7.8104
Max Act: 7.1854. Min Act: -0.1700
Data Index: 8241613 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8104. Min Range: -7.8104
Max Act: 7.1229. Min Act: -0.1700
Data Index: 5604400 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8104. Min Range: -7.8104
Max Act: 7.1542. Min Act: -0.1700
Data Index: 4362942 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8104. Min Range: -7.8104
Max Act: 7.0917. Min Act: -0.1700
Data Index: 6509881 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8104. Min Range: -7.8104
Max Act: 7.0292. Min Act: -0.1700
Data Index: 2559275 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8104. Min Range: -7.8104
Max Act: 6.9979. Min Act: -0.1700
Data Index: 582276 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8104. Min Range: -7.8104
Max Act: 7.0292. Min Act: -0.1697
Data Index: 1619310 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8104. Min Range: -7.8104
Max Act: 6.9667. Min Act: -0.1700
Data Index: 2661600 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19