Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4387 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.2657. Min Act: -0.1700
Data Index: 3093613 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.2345. Min Act: -0.1700
Data Index: 5007887 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1720. Min Act: -0.1700
Data Index: 1532307 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1095. Min Act: -0.1700
Data Index: 6441564 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1407. Min Act: -0.1700
Data Index: 2012117 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.0782. Min Act: -0.1700
Data Index: 1593223 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.0782. Min Act: -0.1700
Data Index: 3040448 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.0470. Min Act: -0.1700
Data Index: 6364205 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2657. Min Range: -5.2657
Max Act: 4.9845. Min Act: -0.1700
Data Index: 5079069 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2657. Min Range: -5.2657
Max Act: 4.9220. Min Act: -0.1700
Data Index: 3122013 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2657. Min Range: -5.2657
Max Act: 4.9220. Min Act: -0.1700
Data Index: 8637194 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2657. Min Range: -5.2657
Max Act: 4.9220. Min Act: -0.1700
Data Index: 309376 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2657. Min Range: -5.2657
Max Act: 4.9220. Min Act: -0.1700
Data Index: 3997427 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2657. Min Range: -5.2657
Max Act: 4.8907. Min Act: -0.1700
Data Index: 6324136 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2657. Min Range: -5.2657
Max Act: 4.8907. Min Act: -0.1700
Data Index: 3007021 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2657. Min Range: -5.2657
Max Act: 4.9220. Min Act: -0.1700
Data Index: 3411628 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2657. Min Range: -5.2657
Max Act: 4.8595. Min Act: -0.1700
Data Index: 2611944 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2657. Min Range: -5.2657
Max Act: 4.8595. Min Act: -0.1700
Data Index: 4516557 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2657. Min Range: -5.2657
Max Act: 4.8595. Min Act: -0.1700
Data Index: 8498196 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2657. Min Range: -5.2657
Max Act: 4.8595. Min Act: -0.1700
Data Index: 8508167 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #19