Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1272 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.8846. Min Act: -0.1700
Data Index: 2003086 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.7908. Min Act: -0.1700
Data Index: 4517161 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.8533. Min Act: -0.1700
Data Index: 631419 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.6033. Min Act: -0.1700
Data Index: 7541187 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.5408. Min Act: -0.1700
Data Index: 5845457 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.5096. Min Act: -0.1700
Data Index: 8380250 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.5096. Min Act: -0.1700
Data Index: 5740063 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.4158. Min Act: -0.1700
Data Index: 4797889 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.3846. Min Act: -0.1700
Data Index: 165985 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.3846. Min Act: -0.1700
Data Index: 4535292 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.3533. Min Act: -0.1700
Data Index: 8072304 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.3533. Min Act: -0.1700
Data Index: 7011400 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.3221. Min Act: -0.1700
Data Index: 489060 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.2908. Min Act: -0.1700
Data Index: 3205281 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.2596. Min Act: -0.1700
Data Index: 5190085 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.2908. Min Act: -0.1700
Data Index: 8193024 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.2596. Min Act: -0.1700
Data Index: 2018346 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.2596. Min Act: -0.1700
Data Index: 2792789 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.2596. Min Act: -0.1700
Data Index: 1326994 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.2596. Min Act: -0.1700
Data Index: 3367519 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19