Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1987 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7204. Min Range: -6.7204
Max Act: 6.7204. Min Act: -0.1700
Data Index: 5649295 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7204. Min Range: -6.7204
Max Act: 6.6579. Min Act: -0.1700
Data Index: 4539523 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7204. Min Range: -6.7204
Max Act: 6.4079. Min Act: -0.1700
Data Index: 271574 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7204. Min Range: -6.7204
Max Act: 6.3766. Min Act: -0.1700
Data Index: 8209115 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7204. Min Range: -6.7204
Max Act: 6.2516. Min Act: -0.1700
Data Index: 5224597 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7204. Min Range: -6.7204
Max Act: 6.3141. Min Act: -0.1700
Data Index: 461432 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7204. Min Range: -6.7204
Max Act: 6.2516. Min Act: -0.1700
Data Index: 8521860 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7204. Min Range: -6.7204
Max Act: 6.2516. Min Act: -0.1700
Data Index: 1955220 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7204. Min Range: -6.7204
Max Act: 6.2516. Min Act: -0.1700
Data Index: 2068042 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7204. Min Range: -6.7204
Max Act: 6.2204. Min Act: -0.1700
Data Index: 4073310 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7204. Min Range: -6.7204
Max Act: 6.2204. Min Act: -0.1700
Data Index: 146156 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7204. Min Range: -6.7204
Max Act: 6.1891. Min Act: -0.1700
Data Index: 578785 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7204. Min Range: -6.7204
Max Act: 6.2204. Min Act: -0.1700
Data Index: 3872717 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7204. Min Range: -6.7204
Max Act: 6.2204. Min Act: -0.1700
Data Index: 5423308 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7204. Min Range: -6.7204
Max Act: 6.2204. Min Act: -0.1700
Data Index: 1664035 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7204. Min Range: -6.7204
Max Act: 6.2204. Min Act: -0.1700
Data Index: 3979068 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7204. Min Range: -6.7204
Max Act: 6.2204. Min Act: -0.1700
Data Index: 44793 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7204. Min Range: -6.7204
Max Act: 6.1891. Min Act: -0.1700
Data Index: 4393707 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7204. Min Range: -6.7204
Max Act: 6.2204. Min Act: -0.1700
Data Index: 8587768 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7204. Min Range: -6.7204
Max Act: 6.1266. Min Act: -0.1700
Data Index: 6160250 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19