Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4490 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.5436. Min Act: -0.1700
Data Index: 2426872 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.5280. Min Act: -0.1700
Data Index: 4288872 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.5280. Min Act: -0.1700
Data Index: 1727368 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4810. Min Act: -0.1700
Data Index: 5611534 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4653. Min Act: -0.1700
Data Index: 414281 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4653. Min Act: -0.1700
Data Index: 6098046 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4183. Min Act: -0.1700
Data Index: 2634785 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4340. Min Act: -0.1700
Data Index: 7917113 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4026. Min Act: -0.1700
Data Index: 5547718 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4183. Min Act: -0.1700
Data Index: 5406929 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4026. Min Act: -0.1700
Data Index: 3982873 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3870. Min Act: -0.1700
Data Index: 3267786 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3713. Min Act: -0.1700
Data Index: 4826146 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3713. Min Act: -0.1700
Data Index: 4566233 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3556. Min Act: -0.1700
Data Index: 4975886 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3870. Min Act: -0.1700
Data Index: 1690953 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3870. Min Act: -0.1700
Data Index: 180104 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3713. Min Act: -0.1700
Data Index: 7647853 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3713. Min Act: -0.1700
Data Index: 7012555 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3556. Min Act: -0.1700
Data Index: 4332003 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19