Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 984 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8369. Min Range: -1.8369
Max Act: 1.8369. Min Act: -0.1700
Data Index: 7512037 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8369. Min Range: -1.8369
Max Act: 1.8283. Min Act: -0.1700
Data Index: 4805239 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8369. Min Range: -1.8369
Max Act: 1.8197. Min Act: -0.1700
Data Index: 6018713 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8369. Min Range: -1.8369
Max Act: 1.8025. Min Act: -0.1700
Data Index: 4949775 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8369. Min Range: -1.8369
Max Act: 1.7939. Min Act: -0.1700
Data Index: 7454238 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8369. Min Range: -1.8369
Max Act: 1.7939. Min Act: -0.1700
Data Index: 5652459 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8369. Min Range: -1.8369
Max Act: 1.8025. Min Act: -0.1700
Data Index: 851689 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8369. Min Range: -1.8369
Max Act: 1.7853. Min Act: -0.1700
Data Index: 8209386 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8369. Min Range: -1.8369
Max Act: 1.7767. Min Act: -0.1700
Data Index: 2573471 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8369. Min Range: -1.8369
Max Act: 1.7939. Min Act: -0.1699
Data Index: 7974046 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8369. Min Range: -1.8369
Max Act: 1.7681. Min Act: -0.1700
Data Index: 3023340 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8369. Min Range: -1.8369
Max Act: 1.7508. Min Act: -0.1700
Data Index: 1266515 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8369. Min Range: -1.8369
Max Act: 1.7594. Min Act: -0.1700
Data Index: 3956654 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8369. Min Range: -1.8369
Max Act: 1.7335. Min Act: -0.1700
Data Index: 895777 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8369. Min Range: -1.8369
Max Act: 1.7594. Min Act: -0.1700
Data Index: 662361 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8369. Min Range: -1.8369
Max Act: 1.7508. Min Act: -0.1699
Data Index: 3181256 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8369. Min Range: -1.8369
Max Act: 1.7508. Min Act: -0.1700
Data Index: 2171578 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8369. Min Range: -1.8369
Max Act: 1.7422. Min Act: -0.1700
Data Index: 455056 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8369. Min Range: -1.8369
Max Act: 1.7594. Min Act: -0.1700
Data Index: 5805497 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8369. Min Range: -1.8369
Max Act: 1.7422. Min Act: -0.1700
Data Index: 7542914 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19