Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2872 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6982. Min Range: -8.6982
Max Act: 8.6982. Min Act: -0.1700
Data Index: 2292972 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6982. Min Range: -8.6982
Max Act: 8.3232. Min Act: -0.1700
Data Index: 4765262 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6982. Min Range: -8.6982
Max Act: 8.2607. Min Act: -0.1700
Data Index: 459993 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6982. Min Range: -8.6982
Max Act: 8.2607. Min Act: -0.1700
Data Index: 3889237 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6982. Min Range: -8.6982
Max Act: 8.2607. Min Act: -0.1700
Data Index: 2426356 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6982. Min Range: -8.6982
Max Act: 8.2295. Min Act: -0.1700
Data Index: 3016953 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6982. Min Range: -8.6982
Max Act: 8.1670. Min Act: -0.1700
Data Index: 4333705 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6982. Min Range: -8.6982
Max Act: 8.1045. Min Act: -0.1700
Data Index: 4045803 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6982. Min Range: -8.6982
Max Act: 8.1357. Min Act: -0.1700
Data Index: 6376400 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6982. Min Range: -8.6982
Max Act: 8.1045. Min Act: -0.1700
Data Index: 8731476 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6982. Min Range: -8.6982
Max Act: 8.1045. Min Act: -0.1700
Data Index: 1139010 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6982. Min Range: -8.6982
Max Act: 8.1045. Min Act: -0.1700
Data Index: 5892850 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6982. Min Range: -8.6982
Max Act: 8.0107. Min Act: -0.1700
Data Index: 5283826 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6982. Min Range: -8.6982
Max Act: 8.0420. Min Act: -0.1700
Data Index: 2787898 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6982. Min Range: -8.6982
Max Act: 8.0420. Min Act: -0.1700
Data Index: 6337414 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6982. Min Range: -8.6982
Max Act: 8.0420. Min Act: -0.1700
Data Index: 6242312 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6982. Min Range: -8.6982
Max Act: 8.0107. Min Act: -0.1700
Data Index: 3205190 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6982. Min Range: -8.6982
Max Act: 8.0107. Min Act: -0.1700
Data Index: 3039706 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6982. Min Range: -8.6982
Max Act: 8.0107. Min Act: -0.1700
Data Index: 4916696 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6982. Min Range: -8.6982
Max Act: 7.9795. Min Act: -0.1700
Data Index: 5714782 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19