Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4366 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0648. Min Range: -8.0648
Max Act: 8.0648. Min Act: -0.1700
Data Index: 5444130 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0648. Min Range: -8.0648
Max Act: 7.8148. Min Act: -0.1700
Data Index: 3804318 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0648. Min Range: -8.0648
Max Act: 7.8148. Min Act: -0.1700
Data Index: 3804319 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0648. Min Range: -8.0648
Max Act: 7.5023. Min Act: -0.1700
Data Index: 426466 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0648. Min Range: -8.0648
Max Act: 7.5023. Min Act: -0.1700
Data Index: 4474260 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0648. Min Range: -8.0648
Max Act: 7.4086. Min Act: -0.1700
Data Index: 6725402 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0648. Min Range: -8.0648
Max Act: 7.3773. Min Act: -0.1700
Data Index: 4454070 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0648. Min Range: -8.0648
Max Act: 7.3148. Min Act: -0.1700
Data Index: 4623952 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0648. Min Range: -8.0648
Max Act: 7.3461. Min Act: -0.1700
Data Index: 6796468 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0648. Min Range: -8.0648
Max Act: 7.3148. Min Act: -0.1700
Data Index: 4506591 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0648. Min Range: -8.0648
Max Act: 7.3148. Min Act: -0.1700
Data Index: 4623957 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0648. Min Range: -8.0648
Max Act: 7.3148. Min Act: -0.1700
Data Index: 4623953 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0648. Min Range: -8.0648
Max Act: 7.2836. Min Act: -0.1700
Data Index: 4623956 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0648. Min Range: -8.0648
Max Act: 7.2523. Min Act: -0.1700
Data Index: 4122639 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0648. Min Range: -8.0648
Max Act: 7.2523. Min Act: -0.1700
Data Index: 1041487 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0648. Min Range: -8.0648
Max Act: 7.2211. Min Act: -0.1700
Data Index: 4320468 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0648. Min Range: -8.0648
Max Act: 7.1586. Min Act: -0.1700
Data Index: 7108661 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0648. Min Range: -8.0648
Max Act: 7.1898. Min Act: -0.1700
Data Index: 1138066 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0648. Min Range: -8.0648
Max Act: 7.1898. Min Act: -0.1700
Data Index: 6678678 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0648. Min Range: -8.0648
Max Act: 7.1273. Min Act: -0.1700
Data Index: 1750080 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19