Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2144 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.2616. Min Act: -0.1700
Data Index: 3552920 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.2616. Min Act: -0.1700
Data Index: 5786046 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.2616. Min Act: -0.1700
Data Index: 7090356 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.1991. Min Act: -0.1700
Data Index: 4083353 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.2303. Min Act: -0.1700
Data Index: 2594497 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.1991. Min Act: -0.1700
Data Index: 5730054 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.1991. Min Act: -0.1700
Data Index: 7731319 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.1991. Min Act: -0.1700
Data Index: 3969040 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.1991. Min Act: -0.1700
Data Index: 4059119 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.1678. Min Act: -0.1700
Data Index: 5350341 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.1366. Min Act: -0.1700
Data Index: 2442499 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.1366. Min Act: -0.1700
Data Index: 4829871 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.1366. Min Act: -0.1700
Data Index: 3936797 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.1366. Min Act: -0.1700
Data Index: 6249677 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.1366. Min Act: -0.1700
Data Index: 8712813 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.1366. Min Act: -0.1700
Data Index: 5566487 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.1053. Min Act: -0.1700
Data Index: 7045465 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.1053. Min Act: -0.1700
Data Index: 4679156 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.1053. Min Act: -0.1700
Data Index: 3579477 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.1053. Min Act: -0.1700
Data Index: 1154628 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19