Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6082 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.7082. Min Act: -0.1700
Data Index: 6398662 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.6770. Min Act: -0.1700
Data Index: 4867729 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.6145. Min Act: -0.1700
Data Index: 2702137 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.5520. Min Act: -0.1700
Data Index: 2702136 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.5207. Min Act: -0.1700
Data Index: 5436529 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.5207. Min Act: -0.1699
Data Index: 5387388 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.5207. Min Act: -0.1700
Data Index: 1383792 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.3957. Min Act: -0.1700
Data Index: 1503804 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.3957. Min Act: -0.1700
Data Index: 6514901 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.3644. Min Act: -0.1700
Data Index: 3363304 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.3332. Min Act: -0.1699
Data Index: 8225044 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.3644. Min Act: -0.1700
Data Index: 8039516 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.3332. Min Act: -0.1700
Data Index: 8413550 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.3332. Min Act: -0.1700
Data Index: 6920783 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.3019. Min Act: -0.1700
Data Index: 5875943 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.3019. Min Act: -0.1700
Data Index: 4029778 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.2707. Min Act: -0.1700
Data Index: 5001399 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.2394. Min Act: -0.1700
Data Index: 3743939 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.2394. Min Act: -0.1700
Data Index: 5727359 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.2394. Min Act: -0.1700
Data Index: 2142345 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19