Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2838 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2536. Min Range: -4.2536
Max Act: 4.2224. Min Act: -0.1700
Data Index: 3482461 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2536. Min Range: -4.2536
Max Act: 4.2536. Min Act: -0.1700
Data Index: 2428821 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2536. Min Range: -4.2536
Max Act: 4.1911. Min Act: -0.1700
Data Index: 2243047 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2536. Min Range: -4.2536
Max Act: 4.0973. Min Act: -0.1700
Data Index: 5809280 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2536. Min Range: -4.2536
Max Act: 4.1286. Min Act: -0.1700
Data Index: 7051644 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2536. Min Range: -4.2536
Max Act: 4.0973. Min Act: -0.1700
Data Index: 7613170 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2536. Min Range: -4.2536
Max Act: 4.0348. Min Act: -0.1700
Data Index: 7894190 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2536. Min Range: -4.2536
Max Act: 4.0036. Min Act: -0.1700
Data Index: 1867229 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2536. Min Range: -4.2536
Max Act: 4.0348. Min Act: -0.1700
Data Index: 440008 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2536. Min Range: -4.2536
Max Act: 4.0036. Min Act: -0.1700
Data Index: 3390765 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2536. Min Range: -4.2536
Max Act: 3.9098. Min Act: -0.1700
Data Index: 4252180 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2536. Min Range: -4.2536
Max Act: 3.9723. Min Act: -0.1700
Data Index: 5754427 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2536. Min Range: -4.2536
Max Act: 3.9723. Min Act: -0.1700
Data Index: 395702 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2536. Min Range: -4.2536
Max Act: 3.9410. Min Act: -0.1700
Data Index: 8636392 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2536. Min Range: -4.2536
Max Act: 3.9723. Min Act: -0.1700
Data Index: 4992278 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2536. Min Range: -4.2536
Max Act: 3.9098. Min Act: -0.1700
Data Index: 7325945 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2536. Min Range: -4.2536
Max Act: 3.9098. Min Act: -0.1700
Data Index: 1578038 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2536. Min Range: -4.2536
Max Act: 3.8785. Min Act: -0.1700
Data Index: 3246375 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2536. Min Range: -4.2536
Max Act: 3.9098. Min Act: -0.1700
Data Index: 4458291 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2536. Min Range: -4.2536
Max Act: 3.8472. Min Act: -0.1700
Data Index: 7923103 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19