Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2482 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1505. Min Range: -6.1505
Max Act: 6.1192. Min Act: -0.1700
Data Index: 4615049 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1505. Min Range: -6.1505
Max Act: 6.1505. Min Act: -0.1700
Data Index: 1220826 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1505. Min Range: -6.1505
Max Act: 6.0880. Min Act: -0.1700
Data Index: 6173375 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1505. Min Range: -6.1505
Max Act: 6.0567. Min Act: -0.1700
Data Index: 6746292 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1505. Min Range: -6.1505
Max Act: 5.9942. Min Act: -0.1700
Data Index: 4075514 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1505. Min Range: -6.1505
Max Act: 5.9942. Min Act: -0.1700
Data Index: 2756430 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1505. Min Range: -6.1505
Max Act: 5.9942. Min Act: -0.1700
Data Index: 706736 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1505. Min Range: -6.1505
Max Act: 5.9942. Min Act: -0.1700
Data Index: 5458652 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1505. Min Range: -6.1505
Max Act: 6.0255. Min Act: -0.1700
Data Index: 5746170 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1505. Min Range: -6.1505
Max Act: 5.9630. Min Act: -0.1700
Data Index: 3004500 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1505. Min Range: -6.1505
Max Act: 5.9630. Min Act: -0.1700
Data Index: 2327823 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1505. Min Range: -6.1505
Max Act: 5.9630. Min Act: -0.1700
Data Index: 6746293 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1505. Min Range: -6.1505
Max Act: 5.9630. Min Act: -0.1700
Data Index: 1837610 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1505. Min Range: -6.1505
Max Act: 5.9317. Min Act: -0.1700
Data Index: 505696 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1505. Min Range: -6.1505
Max Act: 5.9317. Min Act: -0.1700
Data Index: 3190485 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1505. Min Range: -6.1505
Max Act: 5.9005. Min Act: -0.1700
Data Index: 3179017 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1505. Min Range: -6.1505
Max Act: 5.8692. Min Act: -0.1700
Data Index: 6172858 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1505. Min Range: -6.1505
Max Act: 5.9005. Min Act: -0.1700
Data Index: 6746272 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1505. Min Range: -6.1505
Max Act: 5.8380. Min Act: -0.1700
Data Index: 336453 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1505. Min Range: -6.1505
Max Act: 5.8692. Min Act: -0.1700
Data Index: 4475184 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19