Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 673 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6369. Min Range: -2.6369
Max Act: 2.6369. Min Act: -0.1700
Data Index: 2962738 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6369. Min Range: -2.6369
Max Act: 2.6369. Min Act: -0.1700
Data Index: 3651673 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6369. Min Range: -2.6369
Max Act: 2.6369. Min Act: -0.1700
Data Index: 1131782 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6369. Min Range: -2.6369
Max Act: 2.6208. Min Act: -0.1700
Data Index: 236505 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6369. Min Range: -2.6369
Max Act: 2.6208. Min Act: -0.1700
Data Index: 2033199 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6369. Min Range: -2.6369
Max Act: 2.5725. Min Act: -0.1700
Data Index: 8586192 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6369. Min Range: -2.6369
Max Act: 2.5725. Min Act: -0.1700
Data Index: 7026067 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6369. Min Range: -2.6369
Max Act: 2.5725. Min Act: -0.1700
Data Index: 5508490 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6369. Min Range: -2.6369
Max Act: 2.5564. Min Act: -0.1700
Data Index: 625388 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6369. Min Range: -2.6369
Max Act: 2.5725. Min Act: -0.1700
Data Index: 4316548 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6369. Min Range: -2.6369
Max Act: 2.5402. Min Act: -0.1700
Data Index: 5038915 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6369. Min Range: -2.6369
Max Act: 2.5402. Min Act: -0.1700
Data Index: 2163010 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6369. Min Range: -2.6369
Max Act: 2.5241. Min Act: -0.1700
Data Index: 3439903 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6369. Min Range: -2.6369
Max Act: 2.4592. Min Act: -0.1700
Data Index: 4054259 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6369. Min Range: -2.6369
Max Act: 2.4592. Min Act: -0.1700
Data Index: 4301955 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6369. Min Range: -2.6369
Max Act: 2.4917. Min Act: -0.1700
Data Index: 5125496 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6369. Min Range: -2.6369
Max Act: 2.4917. Min Act: -0.1700
Data Index: 5439551 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6369. Min Range: -2.6369
Max Act: 2.4755. Min Act: -0.1700
Data Index: 1690055 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6369. Min Range: -2.6369
Max Act: 2.5079. Min Act: -0.1700
Data Index: 1947973 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6369. Min Range: -2.6369
Max Act: 2.4917. Min Act: -0.1700
Data Index: 4954837 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19