Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3395 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.7889. Min Act: -0.1700
Data Index: 8180863 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.7889. Min Act: -0.1700
Data Index: 8486847 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.7577. Min Act: -0.1700
Data Index: 8545836 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.7264. Min Act: -0.1700
Data Index: 1733116 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.6951. Min Act: -0.1700
Data Index: 2962398 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.6951. Min Act: -0.1700
Data Index: 5945355 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.6325. Min Act: -0.1700
Data Index: 367271 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.6012. Min Act: -0.1700
Data Index: 3122624 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.5386. Min Act: -0.1700
Data Index: 3452069 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.6012. Min Act: -0.1700
Data Index: 8197153 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.5699. Min Act: -0.1700
Data Index: 2988088 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.5699. Min Act: -0.1700
Data Index: 2430452 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.5699. Min Act: -0.1700
Data Index: 8703449 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.5699. Min Act: -0.1700
Data Index: 5630245 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.5699. Min Act: -0.1700
Data Index: 7029555 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.5386. Min Act: -0.1700
Data Index: 685470 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.5386. Min Act: -0.1700
Data Index: 2926010 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.5073. Min Act: -0.1700
Data Index: 7313006 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.5386. Min Act: -0.1700
Data Index: 7584394 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.5386. Min Act: -0.1700
Data Index: 807740 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19