Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3446 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 0.4360. Min Range: -0.4360
Max Act: 0.4360. Min Act: -0.1624
Data Index: 8567252 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4360. Min Range: -0.4360
Max Act: 0.3517. Min Act: -0.1699
Data Index: 2329654 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4360. Min Range: -0.4360
Max Act: 0.3381. Min Act: -0.1688
Data Index: 5582868 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4360. Min Range: -0.4360
Max Act: 0.3449. Min Act: -0.1700
Data Index: 2442098 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4360. Min Range: -0.4360
Max Act: 0.3247. Min Act: -0.1700
Data Index: 6621844 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4360. Min Range: -0.4360
Max Act: 0.3314. Min Act: -0.1700
Data Index: 3051875 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4360. Min Range: -0.4360
Max Act: 0.3181. Min Act: -0.1700
Data Index: 7295133 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4360. Min Range: -0.4360
Max Act: 0.2984. Min Act: -0.1699
Data Index: 2446731 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4360. Min Range: -0.4360
Max Act: 0.3115. Min Act: -0.1698
Data Index: 2141415 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4360. Min Range: -0.4360
Max Act: 0.2984. Min Act: -0.1700
Data Index: 6116923 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4360. Min Range: -0.4360
Max Act: 0.2855. Min Act: -0.1700
Data Index: 3099311 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4360. Min Range: -0.4360
Max Act: 0.2855. Min Act: -0.1700
Data Index: 2591543 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4360. Min Range: -0.4360
Max Act: 0.2791. Min Act: -0.1700
Data Index: 3128704 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4360. Min Range: -0.4360
Max Act: 0.2855. Min Act: -0.1700
Data Index: 5795450 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4360. Min Range: -0.4360
Max Act: 0.2791. Min Act: -0.1699
Data Index: 4623674 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4360. Min Range: -0.4360
Max Act: 0.2791. Min Act: -0.1700
Data Index: 3972376 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4360. Min Range: -0.4360
Max Act: 0.2791. Min Act: -0.1700
Data Index: 4132523 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4360. Min Range: -0.4360
Max Act: 0.2791. Min Act: -0.1700
Data Index: 4319276 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4360. Min Range: -0.4360
Max Act: 0.2791. Min Act: -0.1700
Data Index: 401764 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4360. Min Range: -0.4360
Max Act: 0.2727. Min Act: -0.1700
Data Index: 7921026 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19