Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2499 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9993. Min Range: -8.9993
Max Act: 8.8743. Min Act: -0.1700
Data Index: 5833254 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9993. Min Range: -8.9993
Max Act: 8.9368. Min Act: -0.1700
Data Index: 317259 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9993. Min Range: -8.9993
Max Act: 8.9993. Min Act: -0.1700
Data Index: 373628 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9993. Min Range: -8.9993
Max Act: 8.9368. Min Act: -0.1700
Data Index: 5370525 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9993. Min Range: -8.9993
Max Act: 8.8743. Min Act: -0.1700
Data Index: 8166290 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9993. Min Range: -8.9993
Max Act: 8.8743. Min Act: -0.1700
Data Index: 7879840 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9993. Min Range: -8.9993
Max Act: 8.8118. Min Act: -0.1700
Data Index: 6141803 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9993. Min Range: -8.9993
Max Act: 8.7493. Min Act: -0.1700
Data Index: 6989841 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9993. Min Range: -8.9993
Max Act: 8.7493. Min Act: -0.1700
Data Index: 1171772 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9993. Min Range: -8.9993
Max Act: 8.6868. Min Act: -0.1700
Data Index: 409996 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9993. Min Range: -8.9993
Max Act: 8.6243. Min Act: -0.1700
Data Index: 2011826 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9993. Min Range: -8.9993
Max Act: 8.6243. Min Act: -0.1700
Data Index: 2654648 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9993. Min Range: -8.9993
Max Act: 8.6243. Min Act: -0.1700
Data Index: 3685068 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9993. Min Range: -8.9993
Max Act: 8.6243. Min Act: -0.1700
Data Index: 314059 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9993. Min Range: -8.9993
Max Act: 8.5618. Min Act: -0.1700
Data Index: 2498459 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9993. Min Range: -8.9993
Max Act: 8.5618. Min Act: -0.1700
Data Index: 8482214 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9993. Min Range: -8.9993
Max Act: 8.5618. Min Act: -0.1700
Data Index: 7386476 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9993. Min Range: -8.9993
Max Act: 8.4993. Min Act: -0.1700
Data Index: 8209158 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9993. Min Range: -8.9993
Max Act: 8.4993. Min Act: -0.1700
Data Index: 2367783 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9993. Min Range: -8.9993
Max Act: 8.4368. Min Act: -0.1700
Data Index: 5406924 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19