Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 998 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0988. Min Range: -5.0988
Max Act: 5.0676. Min Act: -0.1700
Data Index: 8186304 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0988. Min Range: -5.0988
Max Act: 5.0988. Min Act: -0.1700
Data Index: 4690801 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0988. Min Range: -5.0988
Max Act: 5.0988. Min Act: -0.1700
Data Index: 8570864 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0988. Min Range: -5.0988
Max Act: 5.0676. Min Act: -0.1700
Data Index: 5971902 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0988. Min Range: -5.0988
Max Act: 5.0051. Min Act: -0.1700
Data Index: 1915515 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0988. Min Range: -5.0988
Max Act: 4.9738. Min Act: -0.1700
Data Index: 206726 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0988. Min Range: -5.0988
Max Act: 4.9426. Min Act: -0.1700
Data Index: 6522645 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0988. Min Range: -5.0988
Max Act: 4.9426. Min Act: -0.1700
Data Index: 5406948 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0988. Min Range: -5.0988
Max Act: 4.9426. Min Act: -0.1700
Data Index: 1409203 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0988. Min Range: -5.0988
Max Act: 4.9113. Min Act: -0.1700
Data Index: 2744095 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0988. Min Range: -5.0988
Max Act: 4.8801. Min Act: -0.1700
Data Index: 683324 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0988. Min Range: -5.0988
Max Act: 4.9113. Min Act: -0.1700
Data Index: 4718137 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0988. Min Range: -5.0988
Max Act: 4.9113. Min Act: -0.1700
Data Index: 7106312 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0988. Min Range: -5.0988
Max Act: 4.8801. Min Act: -0.1700
Data Index: 1831307 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0988. Min Range: -5.0988
Max Act: 4.8801. Min Act: -0.1700
Data Index: 4788353 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0988. Min Range: -5.0988
Max Act: 4.8488. Min Act: -0.1700
Data Index: 4333583 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0988. Min Range: -5.0988
Max Act: 4.8488. Min Act: -0.1700
Data Index: 3402348 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0988. Min Range: -5.0988
Max Act: 4.8488. Min Act: -0.1700
Data Index: 3319690 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0988. Min Range: -5.0988
Max Act: 4.8176. Min Act: -0.1700
Data Index: 4470354 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0988. Min Range: -5.0988
Max Act: 4.7551. Min Act: -0.1700
Data Index: 1108758 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19