Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 727 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.3436. Min Range: -10.3436
Max Act: 10.3436. Min Act: -0.1700
Data Index: 8721681 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3436. Min Range: -10.3436
Max Act: 9.2186. Min Act: -0.1700
Data Index: 6234891 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3436. Min Range: -10.3436
Max Act: 9.1561. Min Act: -0.1700
Data Index: 2144485 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3436. Min Range: -10.3436
Max Act: 9.0311. Min Act: -0.1700
Data Index: 8172499 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3436. Min Range: -10.3436
Max Act: 8.8436. Min Act: -0.1700
Data Index: 5131621 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3436. Min Range: -10.3436
Max Act: 8.6561. Min Act: -0.1700
Data Index: 6008054 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3436. Min Range: -10.3436
Max Act: 8.6561. Min Act: -0.1700
Data Index: 5944270 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3436. Min Range: -10.3436
Max Act: 8.6561. Min Act: -0.1700
Data Index: 5099424 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3436. Min Range: -10.3436
Max Act: 8.5936. Min Act: -0.1700
Data Index: 7048008 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3436. Min Range: -10.3436
Max Act: 8.5311. Min Act: -0.1700
Data Index: 6792686 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3436. Min Range: -10.3436
Max Act: 8.5311. Min Act: -0.1700
Data Index: 916875 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3436. Min Range: -10.3436
Max Act: 8.4061. Min Act: -0.1700
Data Index: 727596 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3436. Min Range: -10.3436
Max Act: 8.3436. Min Act: -0.1700
Data Index: 2117716 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3436. Min Range: -10.3436
Max Act: 8.4061. Min Act: -0.1700
Data Index: 8236377 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3436. Min Range: -10.3436
Max Act: 8.4061. Min Act: -0.1700
Data Index: 6166071 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3436. Min Range: -10.3436
Max Act: 8.3436. Min Act: -0.1700
Data Index: 4712 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3436. Min Range: -10.3436
Max Act: 8.3436. Min Act: -0.1700
Data Index: 3569592 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3436. Min Range: -10.3436
Max Act: 8.3436. Min Act: -0.1700
Data Index: 863583 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3436. Min Range: -10.3436
Max Act: 8.3436. Min Act: -0.1700
Data Index: 128110 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3436. Min Range: -10.3436
Max Act: 8.2811. Min Act: -0.1700
Data Index: 5767262 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19