Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1066 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2059. Min Range: -2.2059
Max Act: 2.2059. Min Act: -0.1700
Data Index: 7545509 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2059. Min Range: -2.2059
Max Act: 2.1893. Min Act: -0.1700
Data Index: 5006731 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2059. Min Range: -2.2059
Max Act: 2.1726. Min Act: -0.1700
Data Index: 5938614 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2059. Min Range: -2.2059
Max Act: 2.1560. Min Act: -0.1700
Data Index: 4762966 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2059. Min Range: -2.2059
Max Act: 2.1560. Min Act: -0.1700
Data Index: 4702115 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2059. Min Range: -2.2059
Max Act: 2.1560. Min Act: -0.1700
Data Index: 4399982 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2059. Min Range: -2.2059
Max Act: 2.1393. Min Act: -0.1700
Data Index: 2992567 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2059. Min Range: -2.2059
Max Act: 2.1393. Min Act: -0.1700
Data Index: 3581351 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2059. Min Range: -2.2059
Max Act: 2.1393. Min Act: -0.1700
Data Index: 2632292 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2059. Min Range: -2.2059
Max Act: 2.1226. Min Act: -0.1700
Data Index: 7794336 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2059. Min Range: -2.2059
Max Act: 2.1059. Min Act: -0.1700
Data Index: 2929305 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2059. Min Range: -2.2059
Max Act: 2.0891. Min Act: -0.1700
Data Index: 3109233 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2059. Min Range: -2.2059
Max Act: 2.0891. Min Act: -0.1700
Data Index: 3667883 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2059. Min Range: -2.2059
Max Act: 2.0724. Min Act: -0.1700
Data Index: 1183865 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2059. Min Range: -2.2059
Max Act: 2.0724. Min Act: -0.1700
Data Index: 8484343 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2059. Min Range: -2.2059
Max Act: 2.0724. Min Act: -0.1700
Data Index: 5866495 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2059. Min Range: -2.2059
Max Act: 2.0556. Min Act: -0.1700
Data Index: 3927963 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2059. Min Range: -2.2059
Max Act: 2.0556. Min Act: -0.1700
Data Index: 7434747 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2059. Min Range: -2.2059
Max Act: 2.0556. Min Act: -0.1700
Data Index: 5216580 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2059. Min Range: -2.2059
Max Act: 2.0387. Min Act: -0.1700
Data Index: 3830315 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19