Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2958 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0186. Min Range: -5.0186
Max Act: 5.0186. Min Act: -0.1700
Data Index: 6013657 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0186. Min Range: -5.0186
Max Act: 4.9873. Min Act: -0.1700
Data Index: 1617055 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0186. Min Range: -5.0186
Max Act: 4.9248. Min Act: -0.1700
Data Index: 7029148 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0186. Min Range: -5.0186
Max Act: 4.9561. Min Act: -0.1700
Data Index: 7130783 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0186. Min Range: -5.0186
Max Act: 4.9561. Min Act: -0.1700
Data Index: 7573997 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0186. Min Range: -5.0186
Max Act: 4.9561. Min Act: -0.1700
Data Index: 390919 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0186. Min Range: -5.0186
Max Act: 4.9561. Min Act: -0.1700
Data Index: 8775164 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0186. Min Range: -5.0186
Max Act: 4.9561. Min Act: -0.1700
Data Index: 8087721 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0186. Min Range: -5.0186
Max Act: 4.9561. Min Act: -0.1700
Data Index: 1112469 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0186. Min Range: -5.0186
Max Act: 4.9561. Min Act: -0.1699
Data Index: 8478144 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0186. Min Range: -5.0186
Max Act: 4.9248. Min Act: -0.1700
Data Index: 3039823 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0186. Min Range: -5.0186
Max Act: 4.9248. Min Act: -0.1700
Data Index: 1020886 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0186. Min Range: -5.0186
Max Act: 4.9248. Min Act: -0.1700
Data Index: 8540691 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0186. Min Range: -5.0186
Max Act: 4.9248. Min Act: -0.1700
Data Index: 8516605 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0186. Min Range: -5.0186
Max Act: 4.9248. Min Act: -0.1700
Data Index: 5957874 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0186. Min Range: -5.0186
Max Act: 4.9248. Min Act: -0.1700
Data Index: 3014389 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0186. Min Range: -5.0186
Max Act: 4.9248. Min Act: -0.1700
Data Index: 7707915 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0186. Min Range: -5.0186
Max Act: 4.8936. Min Act: -0.1700
Data Index: 1293898 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0186. Min Range: -5.0186
Max Act: 4.8936. Min Act: -0.1700
Data Index: 1940662 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0186. Min Range: -5.0186
Max Act: 4.8936. Min Act: -0.1700
Data Index: 1361166 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19