Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2050 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5854. Min Range: -5.5854
Max Act: 5.5854. Min Act: -0.1700
Data Index: 5234340 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5854. Min Range: -5.5854
Max Act: 5.4292. Min Act: -0.1700
Data Index: 3992181 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5854. Min Range: -5.5854
Max Act: 5.3667. Min Act: -0.1700
Data Index: 2903470 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5854. Min Range: -5.5854
Max Act: 5.2729. Min Act: -0.1700
Data Index: 2761665 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5854. Min Range: -5.5854
Max Act: 5.2729. Min Act: -0.1700
Data Index: 176036 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5854. Min Range: -5.5854
Max Act: 5.3042. Min Act: -0.1700
Data Index: 5276479 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5854. Min Range: -5.5854
Max Act: 5.2417. Min Act: -0.1700
Data Index: 7270528 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5854. Min Range: -5.5854
Max Act: 5.2104. Min Act: -0.1700
Data Index: 3129170 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5854. Min Range: -5.5854
Max Act: 5.2104. Min Act: -0.1700
Data Index: 4521422 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5854. Min Range: -5.5854
Max Act: 5.2104. Min Act: -0.1700
Data Index: 7103080 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5854. Min Range: -5.5854
Max Act: 5.2104. Min Act: -0.1700
Data Index: 7327193 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5854. Min Range: -5.5854
Max Act: 5.1792. Min Act: -0.1700
Data Index: 7549778 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5854. Min Range: -5.5854
Max Act: 5.1792. Min Act: -0.1700
Data Index: 7570610 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5854. Min Range: -5.5854
Max Act: 5.1479. Min Act: -0.1700
Data Index: 4881756 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5854. Min Range: -5.5854
Max Act: 5.1479. Min Act: -0.1700
Data Index: 2289436 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5854. Min Range: -5.5854
Max Act: 5.1792. Min Act: -0.1700
Data Index: 4658708 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5854. Min Range: -5.5854
Max Act: 5.1479. Min Act: -0.1700
Data Index: 543526 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5854. Min Range: -5.5854
Max Act: 5.1167. Min Act: -0.1700
Data Index: 3523994 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5854. Min Range: -5.5854
Max Act: 5.1167. Min Act: -0.1700
Data Index: 1684014 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5854. Min Range: -5.5854
Max Act: 5.0854. Min Act: -0.1700
Data Index: 6131275 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19