Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 57 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.3067. Min Range: -1.3067
Max Act: 1.3067. Min Act: -0.1700
Data Index: 2641867 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3067. Min Range: -1.3067
Max Act: 1.2714. Min Act: -0.1700
Data Index: 4885474 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3067. Min Range: -1.3067
Max Act: 1.2890. Min Act: -0.1700
Data Index: 4596428 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3067. Min Range: -1.3067
Max Act: 1.2714. Min Act: -0.1695
Data Index: 2166585 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3067. Min Range: -1.3067
Max Act: 1.2538. Min Act: -0.1700
Data Index: 2215175 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3067. Min Range: -1.3067
Max Act: 1.2449. Min Act: -0.1700
Data Index: 6198747 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3067. Min Range: -1.3067
Max Act: 1.2273. Min Act: -0.1700
Data Index: 2522348 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3067. Min Range: -1.3067
Max Act: 1.2361. Min Act: -0.1700
Data Index: 526949 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3067. Min Range: -1.3067
Max Act: 1.2273. Min Act: -0.1700
Data Index: 6041353 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3067. Min Range: -1.3067
Max Act: 1.2449. Min Act: -0.1700
Data Index: 4596427 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3067. Min Range: -1.3067
Max Act: 1.2361. Min Act: -0.1700
Data Index: 4596429 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3067. Min Range: -1.3067
Max Act: 1.2449. Min Act: -0.1700
Data Index: 1483436 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3067. Min Range: -1.3067
Max Act: 1.2273. Min Act: -0.1700
Data Index: 3165511 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3067. Min Range: -1.3067
Max Act: 1.2273. Min Act: -0.1700
Data Index: 6396683 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3067. Min Range: -1.3067
Max Act: 1.2449. Min Act: -0.1700
Data Index: 4926823 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3067. Min Range: -1.3067
Max Act: 1.2449. Min Act: -0.1698
Data Index: 8694731 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3067. Min Range: -1.3067
Max Act: 1.2097. Min Act: -0.1700
Data Index: 5241154 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3067. Min Range: -1.3067
Max Act: 1.2185. Min Act: -0.1700
Data Index: 7005755 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3067. Min Range: -1.3067
Max Act: 1.1921. Min Act: -0.1700
Data Index: 900936 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3067. Min Range: -1.3067
Max Act: 1.2009. Min Act: -0.1700
Data Index: 3275125 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19