Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2386 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 5.6730. Min Range: -5.6730
Max Act: 5.6730. Min Act: -0.1700
Data Index: 7859508 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6730. Min Range: -5.6730
Max Act: 5.4543. Min Act: -0.1700
Data Index: 1885836 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6730. Min Range: -5.6730
Max Act: 5.3293. Min Act: -0.1700
Data Index: 5533565 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6730. Min Range: -5.6730
Max Act: 5.3293. Min Act: -0.1700
Data Index: 2201514 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6730. Min Range: -5.6730
Max Act: 5.2980. Min Act: -0.1700
Data Index: 5155787 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6730. Min Range: -5.6730
Max Act: 5.2355. Min Act: -0.1700
Data Index: 2417379 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6730. Min Range: -5.6730
Max Act: 5.2668. Min Act: -0.1700
Data Index: 5946856 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6730. Min Range: -5.6730
Max Act: 5.2980. Min Act: -0.1700
Data Index: 471751 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6730. Min Range: -5.6730
Max Act: 5.2668. Min Act: -0.1700
Data Index: 2686734 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6730. Min Range: -5.6730
Max Act: 5.2355. Min Act: -0.1700
Data Index: 2587584 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6730. Min Range: -5.6730
Max Act: 5.2043. Min Act: -0.1700
Data Index: 2058026 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6730. Min Range: -5.6730
Max Act: 5.1730. Min Act: -0.1700
Data Index: 3650264 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6730. Min Range: -5.6730
Max Act: 5.2043. Min Act: -0.1700
Data Index: 8728388 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6730. Min Range: -5.6730
Max Act: 5.1730. Min Act: -0.1700
Data Index: 3836756 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6730. Min Range: -5.6730
Max Act: 5.1418. Min Act: -0.1700
Data Index: 8403361 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6730. Min Range: -5.6730
Max Act: 5.0793. Min Act: -0.1700
Data Index: 2578419 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6730. Min Range: -5.6730
Max Act: 5.1105. Min Act: -0.1700
Data Index: 413645 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6730. Min Range: -5.6730
Max Act: 5.0793. Min Act: -0.1700
Data Index: 3720683 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6730. Min Range: -5.6730
Max Act: 5.0793. Min Act: -0.1700
Data Index: 4103623 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6730. Min Range: -5.6730
Max Act: 5.0793. Min Act: -0.1700
Data Index: 5965451 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19