Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5254 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.6226. Min Act: -0.1700
Data Index: 7874702 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.5289. Min Act: -0.1700
Data Index: 2765250 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.5289. Min Act: -0.1700
Data Index: 2434124 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.5601. Min Act: -0.1700
Data Index: 2781530 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.4664. Min Act: -0.1700
Data Index: 3818746 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.3726. Min Act: -0.1700
Data Index: 6013777 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.3414. Min Act: -0.1700
Data Index: 3597286 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.3101. Min Act: -0.1700
Data Index: 1780938 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.2789. Min Act: -0.1700
Data Index: 6568177 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.2476. Min Act: -0.1700
Data Index: 2035245 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.2476. Min Act: -0.1700
Data Index: 6763833 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.2164. Min Act: -0.1700
Data Index: 5317103 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.2164. Min Act: -0.1700
Data Index: 7362429 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.2164. Min Act: -0.1700
Data Index: 8016872 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.1226. Min Act: -0.1700
Data Index: 8705175 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.0601. Min Act: -0.1700
Data Index: 732587 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.0914. Min Act: -0.1700
Data Index: 7649610 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.1226. Min Act: -0.1700
Data Index: 5953348 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.0601. Min Act: -0.1700
Data Index: 4156674 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.0601. Min Act: -0.1700
Data Index: 741712 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19