Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 690 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2763. Min Range: -4.2763
Max Act: 4.2763. Min Act: -0.1700
Data Index: 2631874 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2763. Min Range: -4.2763
Max Act: 4.1200. Min Act: -0.1700
Data Index: 6797267 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2763. Min Range: -4.2763
Max Act: 4.1200. Min Act: -0.1700
Data Index: 5387147 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2763. Min Range: -4.2763
Max Act: 4.0887. Min Act: -0.1700
Data Index: 5836137 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2763. Min Range: -4.2763
Max Act: 4.0575. Min Act: -0.1700
Data Index: 6501240 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2763. Min Range: -4.2763
Max Act: 3.9950. Min Act: -0.1700
Data Index: 1769057 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2763. Min Range: -4.2763
Max Act: 3.9012. Min Act: -0.1700
Data Index: 1362494 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2763. Min Range: -4.2763
Max Act: 3.9012. Min Act: -0.1700
Data Index: 4749489 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2763. Min Range: -4.2763
Max Act: 3.8074. Min Act: -0.1700
Data Index: 4562900 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2763. Min Range: -4.2763
Max Act: 3.8074. Min Act: -0.1700
Data Index: 2364313 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2763. Min Range: -4.2763
Max Act: 3.7917. Min Act: -0.1700
Data Index: 5396855 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2763. Min Range: -4.2763
Max Act: 3.8074. Min Act: -0.1700
Data Index: 1114806 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2763. Min Range: -4.2763
Max Act: 3.7761. Min Act: -0.1700
Data Index: 3623919 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2763. Min Range: -4.2763
Max Act: 3.7761. Min Act: -0.1700
Data Index: 1156305 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2763. Min Range: -4.2763
Max Act: 3.7605. Min Act: -0.1700
Data Index: 4051266 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2763. Min Range: -4.2763
Max Act: 3.7448. Min Act: -0.1700
Data Index: 6819600 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2763. Min Range: -4.2763
Max Act: 3.7292. Min Act: -0.1700
Data Index: 6813019 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2763. Min Range: -4.2763
Max Act: 3.7292. Min Act: -0.1700
Data Index: 1695347 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2763. Min Range: -4.2763
Max Act: 3.7292. Min Act: -0.1700
Data Index: 5252582 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2763. Min Range: -4.2763
Max Act: 3.7292. Min Act: -0.1700
Data Index: 8206782 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19