Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2921 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.4336. Min Act: -0.1700
Data Index: 1799168 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.4024. Min Act: -0.1700
Data Index: 7801550 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.3711. Min Act: -0.1700
Data Index: 8531726 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.2461. Min Act: -0.1700
Data Index: 790839 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.2774. Min Act: -0.1700
Data Index: 181259 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.2461. Min Act: -0.1700
Data Index: 2337117 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.2149. Min Act: -0.1700
Data Index: 1053020 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.2149. Min Act: -0.1700
Data Index: 5743860 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.2149. Min Act: -0.1700
Data Index: 6805974 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.1836. Min Act: -0.1700
Data Index: 23619 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.1836. Min Act: -0.1700
Data Index: 3524727 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.1836. Min Act: -0.1700
Data Index: 7200161 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.1836. Min Act: -0.1700
Data Index: 5702463 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.1524. Min Act: -0.1700
Data Index: 8093547 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.1524. Min Act: -0.1700
Data Index: 1253590 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.1211. Min Act: -0.1700
Data Index: 1964020 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.1524. Min Act: -0.1700
Data Index: 6415904 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.1524. Min Act: -0.1700
Data Index: 7630293 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.1524. Min Act: -0.1700
Data Index: 276904 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.1524. Min Act: -0.1700
Data Index: 2423398 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19