Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1961 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.4286. Min Act: -0.1700
Data Index: 6323543 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.3661. Min Act: -0.1700
Data Index: 8749720 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.3661. Min Act: -0.1700
Data Index: 3807559 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.3661. Min Act: -0.1700
Data Index: 4529301 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.3661. Min Act: -0.1700
Data Index: 84567 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.3036. Min Act: -0.1700
Data Index: 3062998 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.2724. Min Act: -0.1700
Data Index: 5306070 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.2411. Min Act: -0.1700
Data Index: 4425681 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.2724. Min Act: -0.1700
Data Index: 2809654 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.2724. Min Act: -0.1700
Data Index: 2781030 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.2411. Min Act: -0.1700
Data Index: 1536959 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.2099. Min Act: -0.1700
Data Index: 6107237 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.2099. Min Act: -0.1700
Data Index: 1164112 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.2099. Min Act: -0.1700
Data Index: 2687208 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.1786. Min Act: -0.1700
Data Index: 6661933 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.1474. Min Act: -0.1700
Data Index: 4982558 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.1474. Min Act: -0.1700
Data Index: 863108 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.1786. Min Act: -0.1700
Data Index: 2755519 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.1474. Min Act: -0.1700
Data Index: 5082095 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.1786. Min Act: -0.1700
Data Index: 2261693 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19