Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2507 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3037. Min Range: -8.3037
Max Act: 8.3037. Min Act: -0.1700
Data Index: 5370679 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3037. Min Range: -8.3037
Max Act: 8.3037. Min Act: -0.1700
Data Index: 7754533 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3037. Min Range: -8.3037
Max Act: 8.1787. Min Act: -0.1700
Data Index: 1765178 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3037. Min Range: -8.3037
Max Act: 7.9912. Min Act: -0.1700
Data Index: 671109 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3037. Min Range: -8.3037
Max Act: 7.9912. Min Act: -0.1700
Data Index: 3485320 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3037. Min Range: -8.3037
Max Act: 7.9287. Min Act: -0.1700
Data Index: 3753026 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3037. Min Range: -8.3037
Max Act: 7.9287. Min Act: -0.1700
Data Index: 676294 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3037. Min Range: -8.3037
Max Act: 7.8662. Min Act: -0.1700
Data Index: 1069914 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3037. Min Range: -8.3037
Max Act: 7.8037. Min Act: -0.1700
Data Index: 3817989 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3037. Min Range: -8.3037
Max Act: 7.8662. Min Act: -0.1700
Data Index: 366303 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3037. Min Range: -8.3037
Max Act: 7.8037. Min Act: -0.1700
Data Index: 307736 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3037. Min Range: -8.3037
Max Act: 7.8662. Min Act: -0.1700
Data Index: 550135 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3037. Min Range: -8.3037
Max Act: 7.8662. Min Act: -0.1700
Data Index: 6321586 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3037. Min Range: -8.3037
Max Act: 7.8037. Min Act: -0.1700
Data Index: 8830659 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3037. Min Range: -8.3037
Max Act: 7.8037. Min Act: -0.1700
Data Index: 5152211 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3037. Min Range: -8.3037
Max Act: 7.8037. Min Act: -0.1700
Data Index: 5354501 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3037. Min Range: -8.3037
Max Act: 7.7412. Min Act: -0.1700
Data Index: 3419595 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3037. Min Range: -8.3037
Max Act: 7.8037. Min Act: -0.1700
Data Index: 4709153 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3037. Min Range: -8.3037
Max Act: 7.8037. Min Act: -0.1700
Data Index: 878632 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3037. Min Range: -8.3037
Max Act: 7.8662. Min Act: -0.1700
Data Index: 3283696 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19