Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4155 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8299. Min Range: -4.8299
Max Act: 4.8299. Min Act: -0.1700
Data Index: 2884184 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8299. Min Range: -4.8299
Max Act: 4.8299. Min Act: -0.1700
Data Index: 1821060 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8299. Min Range: -4.8299
Max Act: 4.7362. Min Act: -0.1700
Data Index: 8541620 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8299. Min Range: -4.8299
Max Act: 4.6737. Min Act: -0.1700
Data Index: 5490063 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8299. Min Range: -4.8299
Max Act: 4.6424. Min Act: -0.1700
Data Index: 6265649 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8299. Min Range: -4.8299
Max Act: 4.6424. Min Act: -0.1700
Data Index: 416029 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8299. Min Range: -4.8299
Max Act: 4.6737. Min Act: -0.1700
Data Index: 1952608 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8299. Min Range: -4.8299
Max Act: 4.6424. Min Act: -0.1700
Data Index: 1683835 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8299. Min Range: -4.8299
Max Act: 4.6424. Min Act: -0.1700
Data Index: 6674806 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8299. Min Range: -4.8299
Max Act: 4.6424. Min Act: -0.1700
Data Index: 2609874 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8299. Min Range: -4.8299
Max Act: 4.6424. Min Act: -0.1700
Data Index: 113837 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8299. Min Range: -4.8299
Max Act: 4.6112. Min Act: -0.1700
Data Index: 5913678 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8299. Min Range: -4.8299
Max Act: 4.6112. Min Act: -0.1700
Data Index: 6918137 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8299. Min Range: -4.8299
Max Act: 4.6112. Min Act: -0.1700
Data Index: 6673078 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8299. Min Range: -4.8299
Max Act: 4.5799. Min Act: -0.1700
Data Index: 12375 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8299. Min Range: -4.8299
Max Act: 4.5799. Min Act: -0.1700
Data Index: 1061750 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8299. Min Range: -4.8299
Max Act: 4.6112. Min Act: -0.1700
Data Index: 180474 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8299. Min Range: -4.8299
Max Act: 4.5799. Min Act: -0.1700
Data Index: 578755 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8299. Min Range: -4.8299
Max Act: 4.5799. Min Act: -0.1700
Data Index: 4127477 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8299. Min Range: -4.8299
Max Act: 4.5799. Min Act: -0.1700
Data Index: 5983183 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19