Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 573 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4985. Min Range: -1.4985
Max Act: 1.4985. Min Act: -0.1699
Data Index: 399478 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4985. Min Range: -1.4985
Max Act: 1.4897. Min Act: -0.1699
Data Index: 681191 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4985. Min Range: -1.4985
Max Act: 1.4985. Min Act: -0.1700
Data Index: 4775682 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4985. Min Range: -1.4985
Max Act: 1.4897. Min Act: -0.1700
Data Index: 4640073 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4985. Min Range: -1.4985
Max Act: 1.4809. Min Act: -0.1697
Data Index: 3473284 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4985. Min Range: -1.4985
Max Act: 1.4809. Min Act: -0.1700
Data Index: 5965351 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4985. Min Range: -1.4985
Max Act: 1.4633. Min Act: -0.1700
Data Index: 1255531 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4985. Min Range: -1.4985
Max Act: 1.4633. Min Act: -0.1697
Data Index: 2345734 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4985. Min Range: -1.4985
Max Act: 1.4633. Min Act: -0.1700
Data Index: 1299230 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4985. Min Range: -1.4985
Max Act: 1.4633. Min Act: -0.1700
Data Index: 4570611 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4985. Min Range: -1.4985
Max Act: 1.4545. Min Act: -0.1700
Data Index: 3553537 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4985. Min Range: -1.4985
Max Act: 1.4457. Min Act: -0.1700
Data Index: 224527 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4985. Min Range: -1.4985
Max Act: 1.4457. Min Act: -0.1700
Data Index: 2710999 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4985. Min Range: -1.4985
Max Act: 1.4545. Min Act: -0.1700
Data Index: 2821960 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4985. Min Range: -1.4985
Max Act: 1.4457. Min Act: -0.1697
Data Index: 2632923 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4985. Min Range: -1.4985
Max Act: 1.4369. Min Act: -0.1696
Data Index: 2179411 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4985. Min Range: -1.4985
Max Act: 1.4369. Min Act: -0.1700
Data Index: 3518134 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4985. Min Range: -1.4985
Max Act: 1.4457. Min Act: -0.1699
Data Index: 3956168 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4985. Min Range: -1.4985
Max Act: 1.4457. Min Act: -0.1700
Data Index: 5730521 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4985. Min Range: -1.4985
Max Act: 1.4281. Min Act: -0.1700
Data Index: 5506893 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19