Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3052 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9453. Min Range: -1.9453
Max Act: 1.9453. Min Act: -0.1699
Data Index: 6485218 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9453. Min Range: -1.9453
Max Act: 1.9028. Min Act: -0.1700
Data Index: 5755579 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9453. Min Range: -1.9453
Max Act: 1.8943. Min Act: -0.1700
Data Index: 3286522 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9453. Min Range: -1.9453
Max Act: 1.8686. Min Act: -0.1700
Data Index: 8448953 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9453. Min Range: -1.9453
Max Act: 1.8515. Min Act: -0.1700
Data Index: 6515278 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9453. Min Range: -1.9453
Max Act: 1.8515. Min Act: -0.1700
Data Index: 211713 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9453. Min Range: -1.9453
Max Act: 1.8430. Min Act: -0.1700
Data Index: 4280680 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9453. Min Range: -1.9453
Max Act: 1.8344. Min Act: -0.1700
Data Index: 8356657 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9453. Min Range: -1.9453
Max Act: 1.8258. Min Act: -0.1700
Data Index: 7734625 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9453. Min Range: -1.9453
Max Act: 1.8258. Min Act: -0.1700
Data Index: 6261265 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9453. Min Range: -1.9453
Max Act: 1.8258. Min Act: -0.1700
Data Index: 7787518 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9453. Min Range: -1.9453
Max Act: 1.8086. Min Act: -0.1700
Data Index: 3887256 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9453. Min Range: -1.9453
Max Act: 1.8086. Min Act: -0.1700
Data Index: 3929437 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9453. Min Range: -1.9453
Max Act: 1.8000. Min Act: -0.1700
Data Index: 727428 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9453. Min Range: -1.9453
Max Act: 1.8172. Min Act: -0.1700
Data Index: 4305073 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9453. Min Range: -1.9453
Max Act: 1.8000. Min Act: -0.1700
Data Index: 5301008 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9453. Min Range: -1.9453
Max Act: 1.8086. Min Act: -0.1700
Data Index: 2896529 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9453. Min Range: -1.9453
Max Act: 1.8000. Min Act: -0.1700
Data Index: 8611844 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9453. Min Range: -1.9453
Max Act: 1.8000. Min Act: -0.1700
Data Index: 400357 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9453. Min Range: -1.9453
Max Act: 1.8000. Min Act: -0.1700
Data Index: 7751703 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19