Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1045 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1269. Min Range: -6.1269
Max Act: 6.1269. Min Act: -0.1700
Data Index: 4868013 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1269. Min Range: -6.1269
Max Act: 6.0331. Min Act: -0.1700
Data Index: 8148361 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1269. Min Range: -6.1269
Max Act: 6.0644. Min Act: -0.1700
Data Index: 2463667 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1269. Min Range: -6.1269
Max Act: 5.9706. Min Act: -0.1700
Data Index: 6275424 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1269. Min Range: -6.1269
Max Act: 5.9706. Min Act: -0.1700
Data Index: 2172497 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1269. Min Range: -6.1269
Max Act: 5.9081. Min Act: -0.1700
Data Index: 2896435 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1269. Min Range: -6.1269
Max Act: 5.8769. Min Act: -0.1700
Data Index: 4599595 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1269. Min Range: -6.1269
Max Act: 5.8456. Min Act: -0.1700
Data Index: 743021 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1269. Min Range: -6.1269
Max Act: 5.8769. Min Act: -0.1700
Data Index: 7395965 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1269. Min Range: -6.1269
Max Act: 5.8456. Min Act: -0.1700
Data Index: 5343151 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1269. Min Range: -6.1269
Max Act: 5.8456. Min Act: -0.1700
Data Index: 8556154 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1269. Min Range: -6.1269
Max Act: 5.8144. Min Act: -0.1700
Data Index: 4086500 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1269. Min Range: -6.1269
Max Act: 5.8769. Min Act: -0.1700
Data Index: 7063718 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1269. Min Range: -6.1269
Max Act: 5.8144. Min Act: -0.1700
Data Index: 6609490 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1269. Min Range: -6.1269
Max Act: 5.8144. Min Act: -0.1700
Data Index: 5585895 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1269. Min Range: -6.1269
Max Act: 5.7831. Min Act: -0.1700
Data Index: 7042305 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1269. Min Range: -6.1269
Max Act: 5.8144. Min Act: -0.1700
Data Index: 2960419 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1269. Min Range: -6.1269
Max Act: 5.8144. Min Act: -0.1700
Data Index: 2667600 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1269. Min Range: -6.1269
Max Act: 5.7519. Min Act: -0.1700
Data Index: 5442274 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1269. Min Range: -6.1269
Max Act: 5.7519. Min Act: -0.1700
Data Index: 6198677 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19