Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1883 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7159. Min Range: -6.7159
Max Act: 6.7159. Min Act: -0.1700
Data Index: 7517786 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7159. Min Range: -6.7159
Max Act: 6.6221. Min Act: -0.1700
Data Index: 4909903 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7159. Min Range: -6.7159
Max Act: 6.5284. Min Act: -0.1700
Data Index: 5646689 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7159. Min Range: -6.7159
Max Act: 6.4971. Min Act: -0.1700
Data Index: 3230507 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7159. Min Range: -6.7159
Max Act: 6.4346. Min Act: -0.1700
Data Index: 3604066 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7159. Min Range: -6.7159
Max Act: 6.3409. Min Act: -0.1700
Data Index: 3195922 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7159. Min Range: -6.7159
Max Act: 6.2784. Min Act: -0.1700
Data Index: 3107544 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7159. Min Range: -6.7159
Max Act: 6.2784. Min Act: -0.1700
Data Index: 741108 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7159. Min Range: -6.7159
Max Act: 6.2784. Min Act: -0.1700
Data Index: 4413757 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7159. Min Range: -6.7159
Max Act: 6.2784. Min Act: -0.1700
Data Index: 3965279 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7159. Min Range: -6.7159
Max Act: 6.2159. Min Act: -0.1700
Data Index: 7658667 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7159. Min Range: -6.7159
Max Act: 6.2471. Min Act: -0.1700
Data Index: 4328496 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7159. Min Range: -6.7159
Max Act: 6.2159. Min Act: -0.1700
Data Index: 989634 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7159. Min Range: -6.7159
Max Act: 6.1846. Min Act: -0.1700
Data Index: 6389568 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7159. Min Range: -6.7159
Max Act: 6.1534. Min Act: -0.1700
Data Index: 6982903 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7159. Min Range: -6.7159
Max Act: 6.1534. Min Act: -0.1700
Data Index: 2838446 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7159. Min Range: -6.7159
Max Act: 6.1534. Min Act: -0.1700
Data Index: 648688 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7159. Min Range: -6.7159
Max Act: 6.1534. Min Act: -0.1700
Data Index: 3981481 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7159. Min Range: -6.7159
Max Act: 6.1221. Min Act: -0.1700
Data Index: 1977882 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7159. Min Range: -6.7159
Max Act: 6.1221. Min Act: -0.1700
Data Index: 5907140 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19