Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3459 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2413. Min Range: -2.2413
Max Act: 2.2413. Min Act: -0.1700
Data Index: 2619684 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2413. Min Range: -2.2413
Max Act: 2.2247. Min Act: -0.1700
Data Index: 8279980 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2413. Min Range: -2.2413
Max Act: 2.1249. Min Act: -0.1700
Data Index: 6995087 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2413. Min Range: -2.2413
Max Act: 2.1416. Min Act: -0.1700
Data Index: 8454569 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2413. Min Range: -2.2413
Max Act: 2.1249. Min Act: -0.1700
Data Index: 8032754 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2413. Min Range: -2.2413
Max Act: 2.1249. Min Act: -0.1700
Data Index: 4198274 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2413. Min Range: -2.2413
Max Act: 2.1249. Min Act: -0.1700
Data Index: 3367699 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2413. Min Range: -2.2413
Max Act: 2.1082. Min Act: -0.1700
Data Index: 876276 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2413. Min Range: -2.2413
Max Act: 2.0915. Min Act: -0.1700
Data Index: 5712598 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2413. Min Range: -2.2413
Max Act: 2.0747. Min Act: -0.1700
Data Index: 4541677 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2413. Min Range: -2.2413
Max Act: 2.0579. Min Act: -0.1700
Data Index: 6975345 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2413. Min Range: -2.2413
Max Act: 2.0411. Min Act: -0.1700
Data Index: 8066103 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2413. Min Range: -2.2413
Max Act: 2.0411. Min Act: -0.1700
Data Index: 658874 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2413. Min Range: -2.2413
Max Act: 2.0411. Min Act: -0.1700
Data Index: 2355425 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2413. Min Range: -2.2413
Max Act: 2.0411. Min Act: -0.1700
Data Index: 3938125 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2413. Min Range: -2.2413
Max Act: 2.0579. Min Act: -0.1700
Data Index: 5130489 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2413. Min Range: -2.2413
Max Act: 2.0074. Min Act: -0.1700
Data Index: 6090218 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2413. Min Range: -2.2413
Max Act: 2.0411. Min Act: -0.1700
Data Index: 8596726 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2413. Min Range: -2.2413
Max Act: 2.0579. Min Act: -0.1700
Data Index: 6341953 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2413. Min Range: -2.2413
Max Act: 2.0411. Min Act: -0.1700
Data Index: 6211502 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19