Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4692 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8322. Min Range: -4.8322
Max Act: 4.8322. Min Act: -0.1700
Data Index: 2709389 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8322. Min Range: -4.8322
Max Act: 4.7385. Min Act: -0.1700
Data Index: 2821201 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8322. Min Range: -4.8322
Max Act: 4.6760. Min Act: -0.1700
Data Index: 5122328 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8322. Min Range: -4.8322
Max Act: 4.6135. Min Act: -0.1700
Data Index: 4777530 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8322. Min Range: -4.8322
Max Act: 4.6135. Min Act: -0.1699
Data Index: 8279582 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8322. Min Range: -4.8322
Max Act: 4.6135. Min Act: -0.1700
Data Index: 5122330 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8322. Min Range: -4.8322
Max Act: 4.5822. Min Act: -0.1700
Data Index: 3384381 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8322. Min Range: -4.8322
Max Act: 4.5510. Min Act: -0.1700
Data Index: 8030218 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8322. Min Range: -4.8322
Max Act: 4.5510. Min Act: -0.1700
Data Index: 3223707 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8322. Min Range: -4.8322
Max Act: 4.5510. Min Act: -0.1700
Data Index: 5807225 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8322. Min Range: -4.8322
Max Act: 4.5510. Min Act: -0.1700
Data Index: 5859068 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8322. Min Range: -4.8322
Max Act: 4.4885. Min Act: -0.1700
Data Index: 642939 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8322. Min Range: -4.8322
Max Act: 4.4885. Min Act: -0.1700
Data Index: 1412686 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8322. Min Range: -4.8322
Max Act: 4.4572. Min Act: -0.1700
Data Index: 2697194 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8322. Min Range: -4.8322
Max Act: 4.4572. Min Act: -0.1700
Data Index: 6428785 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8322. Min Range: -4.8322
Max Act: 4.4259. Min Act: -0.1700
Data Index: 8534827 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8322. Min Range: -4.8322
Max Act: 4.4572. Min Act: -0.1700
Data Index: 8387483 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8322. Min Range: -4.8322
Max Act: 4.4572. Min Act: -0.1700
Data Index: 4503522 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8322. Min Range: -4.8322
Max Act: 4.4885. Min Act: -0.1700
Data Index: 6685694 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8322. Min Range: -4.8322
Max Act: 4.4572. Min Act: -0.1700
Data Index: 2056745 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19