Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1024 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6603. Min Range: -5.6603
Max Act: 5.6603. Min Act: -0.1700
Data Index: 7742289 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6603. Min Range: -5.6603
Max Act: 5.0665. Min Act: -0.1700
Data Index: 3567831 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6603. Min Range: -5.6603
Max Act: 4.9103. Min Act: -0.1700
Data Index: 5785660 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6603. Min Range: -5.6603
Max Act: 4.8478. Min Act: -0.1700
Data Index: 3041041 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6603. Min Range: -5.6603
Max Act: 4.8165. Min Act: -0.1700
Data Index: 7065768 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6603. Min Range: -5.6603
Max Act: 4.7540. Min Act: -0.1700
Data Index: 2968758 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6603. Min Range: -5.6603
Max Act: 4.7853. Min Act: -0.1700
Data Index: 7451399 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6603. Min Range: -5.6603
Max Act: 4.7540. Min Act: -0.1700
Data Index: 3334171 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6603. Min Range: -5.6603
Max Act: 4.7540. Min Act: -0.1700
Data Index: 2936199 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6603. Min Range: -5.6603
Max Act: 4.7540. Min Act: -0.1700
Data Index: 4236040 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6603. Min Range: -5.6603
Max Act: 4.7228. Min Act: -0.1700
Data Index: 3357545 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6603. Min Range: -5.6603
Max Act: 4.7228. Min Act: -0.1700
Data Index: 2680359 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6603. Min Range: -5.6603
Max Act: 4.7228. Min Act: -0.1700
Data Index: 4977471 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6603. Min Range: -5.6603
Max Act: 4.7540. Min Act: -0.1700
Data Index: 6603751 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6603. Min Range: -5.6603
Max Act: 4.7540. Min Act: -0.1700
Data Index: 297945 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6603. Min Range: -5.6603
Max Act: 4.7228. Min Act: -0.1700
Data Index: 2746647 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6603. Min Range: -5.6603
Max Act: 4.7228. Min Act: -0.1700
Data Index: 5485804 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6603. Min Range: -5.6603
Max Act: 4.6915. Min Act: -0.1700
Data Index: 4423758 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6603. Min Range: -5.6603
Max Act: 4.6915. Min Act: -0.1700
Data Index: 1180441 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6603. Min Range: -5.6603
Max Act: 4.6915. Min Act: -0.1700
Data Index: 552275 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19