Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4582 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2399. Min Range: -7.2399
Max Act: 7.2399. Min Act: -0.1700
Data Index: 4066298 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2399. Min Range: -7.2399
Max Act: 7.1149. Min Act: -0.1700
Data Index: 366025 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2399. Min Range: -7.2399
Max Act: 7.0211. Min Act: -0.1700
Data Index: 1275687 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2399. Min Range: -7.2399
Max Act: 6.9899. Min Act: -0.1700
Data Index: 8751123 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2399. Min Range: -7.2399
Max Act: 6.9899. Min Act: -0.1700
Data Index: 7752888 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2399. Min Range: -7.2399
Max Act: 6.9274. Min Act: -0.1700
Data Index: 7437843 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2399. Min Range: -7.2399
Max Act: 6.8649. Min Act: -0.1700
Data Index: 4944092 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2399. Min Range: -7.2399
Max Act: 6.8336. Min Act: -0.1700
Data Index: 611155 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2399. Min Range: -7.2399
Max Act: 6.7711. Min Act: -0.1700
Data Index: 3978964 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2399. Min Range: -7.2399
Max Act: 6.8024. Min Act: -0.1700
Data Index: 1724179 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2399. Min Range: -7.2399
Max Act: 6.8024. Min Act: -0.1700
Data Index: 8646267 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2399. Min Range: -7.2399
Max Act: 6.8336. Min Act: -0.1700
Data Index: 2865444 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2399. Min Range: -7.2399
Max Act: 6.7711. Min Act: -0.1700
Data Index: 8313209 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2399. Min Range: -7.2399
Max Act: 6.7711. Min Act: -0.1700
Data Index: 7890503 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2399. Min Range: -7.2399
Max Act: 6.7711. Min Act: -0.1700
Data Index: 4903297 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2399. Min Range: -7.2399
Max Act: 6.7399. Min Act: -0.1700
Data Index: 3458105 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2399. Min Range: -7.2399
Max Act: 6.7399. Min Act: -0.1700
Data Index: 1838160 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2399. Min Range: -7.2399
Max Act: 6.7399. Min Act: -0.1700
Data Index: 7998193 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2399. Min Range: -7.2399
Max Act: 6.6774. Min Act: -0.1700
Data Index: 8292954 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2399. Min Range: -7.2399
Max Act: 6.6774. Min Act: -0.1700
Data Index: 61152 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19