Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2787 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6301. Min Range: -7.6301
Max Act: 7.6301. Min Act: -0.1700
Data Index: 2202289 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6301. Min Range: -7.6301
Max Act: 7.2239. Min Act: -0.1700
Data Index: 8653496 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6301. Min Range: -7.6301
Max Act: 7.0364. Min Act: -0.1700
Data Index: 3204153 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6301. Min Range: -7.6301
Max Act: 6.9426. Min Act: -0.1700
Data Index: 3027478 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6301. Min Range: -7.6301
Max Act: 7.0051. Min Act: -0.1700
Data Index: 4370706 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6301. Min Range: -7.6301
Max Act: 6.9426. Min Act: -0.1700
Data Index: 6661638 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6301. Min Range: -7.6301
Max Act: 6.8801. Min Act: -0.1700
Data Index: 285778 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6301. Min Range: -7.6301
Max Act: 6.8176. Min Act: -0.1700
Data Index: 5160055 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6301. Min Range: -7.6301
Max Act: 6.7864. Min Act: -0.1700
Data Index: 3013300 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6301. Min Range: -7.6301
Max Act: 6.8176. Min Act: -0.1700
Data Index: 2832118 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6301. Min Range: -7.6301
Max Act: 6.7551. Min Act: -0.1700
Data Index: 6685112 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6301. Min Range: -7.6301
Max Act: 6.7551. Min Act: -0.1700
Data Index: 5467170 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6301. Min Range: -7.6301
Max Act: 6.7551. Min Act: -0.1700
Data Index: 8022252 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6301. Min Range: -7.6301
Max Act: 6.7551. Min Act: -0.1700
Data Index: 5898198 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6301. Min Range: -7.6301
Max Act: 6.7551. Min Act: -0.1700
Data Index: 7985383 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6301. Min Range: -7.6301
Max Act: 6.7551. Min Act: -0.1700
Data Index: 4210943 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6301. Min Range: -7.6301
Max Act: 6.6926. Min Act: -0.1700
Data Index: 7726736 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6301. Min Range: -7.6301
Max Act: 6.6926. Min Act: -0.1700
Data Index: 4464319 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6301. Min Range: -7.6301
Max Act: 6.5989. Min Act: -0.1700
Data Index: 1043396 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6301. Min Range: -7.6301
Max Act: 6.6614. Min Act: -0.1700
Data Index: 5875631 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19