Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1000 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.9868. Min Act: -0.1700
Data Index: 5829265 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.9868. Min Act: -0.1700
Data Index: 1791865 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.9243. Min Act: -0.1700
Data Index: 3562042 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.8306. Min Act: -0.1700
Data Index: 2082511 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.8306. Min Act: -0.1700
Data Index: 7802236 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.8306. Min Act: -0.1700
Data Index: 4398011 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.7993. Min Act: -0.1700
Data Index: 4768421 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.7368. Min Act: -0.1700
Data Index: 7638811 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.7368. Min Act: -0.1700
Data Index: 1536702 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.7368. Min Act: -0.1700
Data Index: 7087497 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.7056. Min Act: -0.1700
Data Index: 8587773 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.7056. Min Act: -0.1700
Data Index: 8770161 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.7056. Min Act: -0.1700
Data Index: 3818322 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.7056. Min Act: -0.1700
Data Index: 1252964 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.7056. Min Act: -0.1700
Data Index: 3822210 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.6743. Min Act: -0.1700
Data Index: 831440 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.6743. Min Act: -0.1700
Data Index: 5678303 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.6743. Min Act: -0.1700
Data Index: 1252965 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.6743. Min Act: -0.1700
Data Index: 525478 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.6743. Min Act: -0.1700
Data Index: 2386675 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19