Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3012 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4917. Min Range: -5.4917
Max Act: 5.4917. Min Act: -0.1700
Data Index: 5999231 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4917. Min Range: -5.4917
Max Act: 5.3979. Min Act: -0.1700
Data Index: 201139 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4917. Min Range: -5.4917
Max Act: 5.3667. Min Act: -0.1700
Data Index: 2676703 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4917. Min Range: -5.4917
Max Act: 5.3354. Min Act: -0.1700
Data Index: 5709207 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4917. Min Range: -5.4917
Max Act: 5.3354. Min Act: -0.1700
Data Index: 1798477 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4917. Min Range: -5.4917
Max Act: 5.3354. Min Act: -0.1700
Data Index: 7189515 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4917. Min Range: -5.4917
Max Act: 5.3042. Min Act: -0.1700
Data Index: 1922129 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4917. Min Range: -5.4917
Max Act: 5.2729. Min Act: -0.1700
Data Index: 4241211 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4917. Min Range: -5.4917
Max Act: 5.2729. Min Act: -0.1700
Data Index: 8262436 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4917. Min Range: -5.4917
Max Act: 5.2729. Min Act: -0.1700
Data Index: 1092433 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4917. Min Range: -5.4917
Max Act: 5.2729. Min Act: -0.1700
Data Index: 6491264 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4917. Min Range: -5.4917
Max Act: 5.2104. Min Act: -0.1700
Data Index: 3264344 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4917. Min Range: -5.4917
Max Act: 5.2417. Min Act: -0.1700
Data Index: 1040220 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4917. Min Range: -5.4917
Max Act: 5.2729. Min Act: -0.1700
Data Index: 3969421 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4917. Min Range: -5.4917
Max Act: 5.2417. Min Act: -0.1700
Data Index: 6628867 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4917. Min Range: -5.4917
Max Act: 5.1792. Min Act: -0.1700
Data Index: 7890208 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4917. Min Range: -5.4917
Max Act: 5.1792. Min Act: -0.1700
Data Index: 2931078 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4917. Min Range: -5.4917
Max Act: 5.1792. Min Act: -0.1700
Data Index: 5508823 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4917. Min Range: -5.4917
Max Act: 5.1792. Min Act: -0.1700
Data Index: 4994983 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4917. Min Range: -5.4917
Max Act: 5.1479. Min Act: -0.1700
Data Index: 2555302 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19