Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1555 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7269. Min Range: -7.7269
Max Act: 7.7269. Min Act: -0.1700
Data Index: 618468 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7269. Min Range: -7.7269
Max Act: 7.3519. Min Act: -0.1700
Data Index: 2085277 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7269. Min Range: -7.7269
Max Act: 7.3519. Min Act: -0.1700
Data Index: 6358324 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7269. Min Range: -7.7269
Max Act: 7.2894. Min Act: -0.1700
Data Index: 4990708 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7269. Min Range: -7.7269
Max Act: 7.2582. Min Act: -0.1700
Data Index: 320704 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7269. Min Range: -7.7269
Max Act: 7.2269. Min Act: -0.1700
Data Index: 225532 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7269. Min Range: -7.7269
Max Act: 7.1957. Min Act: -0.1700
Data Index: 5515032 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7269. Min Range: -7.7269
Max Act: 7.2269. Min Act: -0.1700
Data Index: 1038043 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7269. Min Range: -7.7269
Max Act: 7.1957. Min Act: -0.1700
Data Index: 5237780 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7269. Min Range: -7.7269
Max Act: 7.1644. Min Act: -0.1700
Data Index: 4288594 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7269. Min Range: -7.7269
Max Act: 7.1332. Min Act: -0.1700
Data Index: 3360852 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7269. Min Range: -7.7269
Max Act: 7.1019. Min Act: -0.1700
Data Index: 2046195 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7269. Min Range: -7.7269
Max Act: 7.1019. Min Act: -0.1700
Data Index: 1325317 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7269. Min Range: -7.7269
Max Act: 7.1019. Min Act: -0.1700
Data Index: 5547910 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7269. Min Range: -7.7269
Max Act: 7.1019. Min Act: -0.1700
Data Index: 6249236 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7269. Min Range: -7.7269
Max Act: 7.0707. Min Act: -0.1700
Data Index: 3110868 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7269. Min Range: -7.7269
Max Act: 7.0707. Min Act: -0.1700
Data Index: 7705339 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7269. Min Range: -7.7269
Max Act: 7.1019. Min Act: -0.1700
Data Index: 8324252 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7269. Min Range: -7.7269
Max Act: 7.0707. Min Act: -0.1700
Data Index: 6867748 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7269. Min Range: -7.7269
Max Act: 7.0394. Min Act: -0.1700
Data Index: 254148 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19