Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2819 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8188. Min Range: -4.8188
Max Act: 4.8188. Min Act: -0.1700
Data Index: 4367497 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8188. Min Range: -4.8188
Max Act: 4.7563. Min Act: -0.1700
Data Index: 8193677 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8188. Min Range: -4.8188
Max Act: 4.7250. Min Act: -0.1700
Data Index: 191288 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8188. Min Range: -4.8188
Max Act: 4.7250. Min Act: -0.1700
Data Index: 247376 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8188. Min Range: -4.8188
Max Act: 4.6938. Min Act: -0.1700
Data Index: 7366589 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8188. Min Range: -4.8188
Max Act: 4.6625. Min Act: -0.1700
Data Index: 4664803 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8188. Min Range: -4.8188
Max Act: 4.7250. Min Act: -0.1700
Data Index: 3348066 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8188. Min Range: -4.8188
Max Act: 4.6938. Min Act: -0.1700
Data Index: 4664802 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8188. Min Range: -4.8188
Max Act: 4.6625. Min Act: -0.1700
Data Index: 601523 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8188. Min Range: -4.8188
Max Act: 4.6938. Min Act: -0.1700
Data Index: 1451409 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8188. Min Range: -4.8188
Max Act: 4.6625. Min Act: -0.1700
Data Index: 1467287 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8188. Min Range: -4.8188
Max Act: 4.6000. Min Act: -0.1700
Data Index: 3627923 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8188. Min Range: -4.8188
Max Act: 4.6313. Min Act: -0.1700
Data Index: 4998646 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8188. Min Range: -4.8188
Max Act: 4.6000. Min Act: -0.1700
Data Index: 7304088 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8188. Min Range: -4.8188
Max Act: 4.5375. Min Act: -0.1700
Data Index: 2171039 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8188. Min Range: -4.8188
Max Act: 4.5375. Min Act: -0.1700
Data Index: 1903510 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8188. Min Range: -4.8188
Max Act: 4.5375. Min Act: -0.1700
Data Index: 3347630 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8188. Min Range: -4.8188
Max Act: 4.5375. Min Act: -0.1700
Data Index: 6906642 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8188. Min Range: -4.8188
Max Act: 4.5375. Min Act: -0.1700
Data Index: 429149 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8188. Min Range: -4.8188
Max Act: 4.5063. Min Act: -0.1700
Data Index: 4429747 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19