Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2451 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2988. Min Range: -4.2988
Max Act: 4.2988. Min Act: -0.1700
Data Index: 7491237 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2988. Min Range: -4.2988
Max Act: 4.2675. Min Act: -0.1700
Data Index: 4863530 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2988. Min Range: -4.2988
Max Act: 4.2363. Min Act: -0.1700
Data Index: 8265559 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2988. Min Range: -4.2988
Max Act: 4.2363. Min Act: -0.1700
Data Index: 7791830 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2988. Min Range: -4.2988
Max Act: 4.1738. Min Act: -0.1700
Data Index: 2054230 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2988. Min Range: -4.2988
Max Act: 4.1738. Min Act: -0.1700
Data Index: 3266443 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2988. Min Range: -4.2988
Max Act: 4.1738. Min Act: -0.1700
Data Index: 3228490 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2988. Min Range: -4.2988
Max Act: 4.1738. Min Act: -0.1700
Data Index: 2882400 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2988. Min Range: -4.2988
Max Act: 4.1738. Min Act: -0.1700
Data Index: 2304354 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2988. Min Range: -4.2988
Max Act: 4.1738. Min Act: -0.1700
Data Index: 5199854 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2988. Min Range: -4.2988
Max Act: 4.1738. Min Act: -0.1700
Data Index: 5912042 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2988. Min Range: -4.2988
Max Act: 4.1425. Min Act: -0.1700
Data Index: 8204198 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2988. Min Range: -4.2988
Max Act: 4.1425. Min Act: -0.1700
Data Index: 7859344 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2988. Min Range: -4.2988
Max Act: 4.1425. Min Act: -0.1700
Data Index: 271612 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2988. Min Range: -4.2988
Max Act: 4.1425. Min Act: -0.1700
Data Index: 6882768 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2988. Min Range: -4.2988
Max Act: 4.1425. Min Act: -0.1700
Data Index: 1206882 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2988. Min Range: -4.2988
Max Act: 4.1425. Min Act: -0.1700
Data Index: 7671418 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2988. Min Range: -4.2988
Max Act: 4.0800. Min Act: -0.1700
Data Index: 5012331 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2988. Min Range: -4.2988
Max Act: 4.1113. Min Act: -0.1700
Data Index: 4803923 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2988. Min Range: -4.2988
Max Act: 4.1113. Min Act: -0.1700
Data Index: 2449666 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19