Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3506 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1293. Min Range: -4.1293
Max Act: 4.1293. Min Act: -0.1700
Data Index: 1576988 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1293. Min Range: -4.1293
Max Act: 3.9105. Min Act: -0.1700
Data Index: 4777409 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1293. Min Range: -4.1293
Max Act: 3.8480. Min Act: -0.1700
Data Index: 3463498 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1293. Min Range: -4.1293
Max Act: 3.7541. Min Act: -0.1700
Data Index: 4514081 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1293. Min Range: -4.1293
Max Act: 3.7854. Min Act: -0.1700
Data Index: 1764823 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1293. Min Range: -4.1293
Max Act: 3.7229. Min Act: -0.1700
Data Index: 7410103 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1293. Min Range: -4.1293
Max Act: 3.6603. Min Act: -0.1700
Data Index: 38278 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1293. Min Range: -4.1293
Max Act: 3.6603. Min Act: -0.1700
Data Index: 878479 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1293. Min Range: -4.1293
Max Act: 3.6603. Min Act: -0.1700
Data Index: 7404257 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1293. Min Range: -4.1293
Max Act: 3.6603. Min Act: -0.1700
Data Index: 4436384 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1293. Min Range: -4.1293
Max Act: 3.6603. Min Act: -0.1700
Data Index: 6677097 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1293. Min Range: -4.1293
Max Act: 3.5977. Min Act: -0.1700
Data Index: 1326909 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1293. Min Range: -4.1293
Max Act: 3.5664. Min Act: -0.1700
Data Index: 1263275 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1293. Min Range: -4.1293
Max Act: 3.5977. Min Act: -0.1700
Data Index: 6887172 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1293. Min Range: -4.1293
Max Act: 3.5977. Min Act: -0.1700
Data Index: 8682442 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1293. Min Range: -4.1293
Max Act: 3.5977. Min Act: -0.1700
Data Index: 8599533 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1293. Min Range: -4.1293
Max Act: 3.5664. Min Act: -0.1700
Data Index: 6771162 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1293. Min Range: -4.1293
Max Act: 3.5977. Min Act: -0.1700
Data Index: 6644660 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1293. Min Range: -4.1293
Max Act: 3.5664. Min Act: -0.1700
Data Index: 5711181 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1293. Min Range: -4.1293
Max Act: 3.5664. Min Act: -0.1700
Data Index: 2728403 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19