Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5680 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2675. Min Range: -2.2675
Max Act: 2.2675. Min Act: -0.1700
Data Index: 2409433 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2675. Min Range: -2.2675
Max Act: 2.2510. Min Act: -0.1700
Data Index: 8723978 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2675. Min Range: -2.2675
Max Act: 2.2345. Min Act: -0.1700
Data Index: 4008884 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2675. Min Range: -2.2675
Max Act: 2.2179. Min Act: -0.1699
Data Index: 1770264 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2675. Min Range: -2.2675
Max Act: 2.2179. Min Act: -0.1671
Data Index: 2960709 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2675. Min Range: -2.2675
Max Act: 2.2013. Min Act: -0.1696
Data Index: 307424 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2675. Min Range: -2.2675
Max Act: 2.2179. Min Act: -0.1700
Data Index: 3417557 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2675. Min Range: -2.2675
Max Act: 2.1847. Min Act: -0.1700
Data Index: 2164985 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2675. Min Range: -2.2675
Max Act: 2.1681. Min Act: -0.1700
Data Index: 4963953 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2675. Min Range: -2.2675
Max Act: 2.1514. Min Act: -0.1700
Data Index: 2702678 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2675. Min Range: -2.2675
Max Act: 2.1514. Min Act: -0.1700
Data Index: 2852057 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2675. Min Range: -2.2675
Max Act: 2.1514. Min Act: -0.1700
Data Index: 374801 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2675. Min Range: -2.2675
Max Act: 2.1514. Min Act: -0.1699
Data Index: 5982052 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2675. Min Range: -2.2675
Max Act: 2.1514. Min Act: -0.1667
Data Index: 5146429 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2675. Min Range: -2.2675
Max Act: 2.1514. Min Act: -0.1700
Data Index: 2358050 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2675. Min Range: -2.2675
Max Act: 2.1514. Min Act: -0.1700
Data Index: 4610987 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2675. Min Range: -2.2675
Max Act: 2.1348. Min Act: -0.1667
Data Index: 356519 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2675. Min Range: -2.2675
Max Act: 2.1180. Min Act: -0.1700
Data Index: 4065891 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2675. Min Range: -2.2675
Max Act: 2.1514. Min Act: -0.1699
Data Index: 2560145 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2675. Min Range: -2.2675
Max Act: 2.1348. Min Act: -0.1700
Data Index: 912936 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19