Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1581 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.0439. Min Range: -1.0439
Max Act: 1.0439. Min Act: -0.1698
Data Index: 6325998 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0439. Min Range: -1.0439
Max Act: 0.9917. Min Act: -0.1681
Data Index: 7480022 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0439. Min Range: -1.0439
Max Act: 0.9917. Min Act: -0.1699
Data Index: 2495296 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0439. Min Range: -1.0439
Max Act: 0.9571. Min Act: -0.1699
Data Index: 4485426 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0439. Min Range: -1.0439
Max Act: 0.9485. Min Act: -0.1660
Data Index: 2342878 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0439. Min Range: -1.0439
Max Act: 0.9744. Min Act: -0.1696
Data Index: 5613791 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0439. Min Range: -1.0439
Max Act: 0.9571. Min Act: -0.1700
Data Index: 5871042 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0439. Min Range: -1.0439
Max Act: 0.9485. Min Act: -0.1699
Data Index: 7649846 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0439. Min Range: -1.0439
Max Act: 0.9399. Min Act: -0.1664
Data Index: 8490877 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0439. Min Range: -1.0439
Max Act: 0.9227. Min Act: -0.1600
Data Index: 230960 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0439. Min Range: -1.0439
Max Act: 0.9399. Min Act: -0.1674
Data Index: 2365671 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0439. Min Range: -1.0439
Max Act: 0.9312. Min Act: -0.1700
Data Index: 7649861 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0439. Min Range: -1.0439
Max Act: 0.9227. Min Act: -0.1700
Data Index: 4049741 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0439. Min Range: -1.0439
Max Act: 0.9141. Min Act: -0.1699
Data Index: 4282020 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0439. Min Range: -1.0439
Max Act: 0.9227. Min Act: -0.1700
Data Index: 5539923 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0439. Min Range: -1.0439
Max Act: 0.9141. Min Act: -0.1700
Data Index: 1325804 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0439. Min Range: -1.0439
Max Act: 0.8970. Min Act: -0.1700
Data Index: 7033620 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0439. Min Range: -1.0439
Max Act: 0.8884. Min Act: -0.1700
Data Index: 6837128 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0439. Min Range: -1.0439
Max Act: 0.9055. Min Act: -0.1695
Data Index: 1013326 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0439. Min Range: -1.0439
Max Act: 0.8884. Min Act: -0.1700
Data Index: 4853094 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19