Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2247 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9692. Min Range: -6.9692
Max Act: 6.9692. Min Act: -0.1700
Data Index: 1153743 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9692. Min Range: -6.9692
Max Act: 6.8442. Min Act: -0.1700
Data Index: 5755324 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9692. Min Range: -6.9692
Max Act: 6.7817. Min Act: -0.1700
Data Index: 1905798 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9692. Min Range: -6.9692
Max Act: 6.7817. Min Act: -0.1700
Data Index: 3381191 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9692. Min Range: -6.9692
Max Act: 6.6255. Min Act: -0.1700
Data Index: 2116050 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9692. Min Range: -6.9692
Max Act: 6.6255. Min Act: -0.1700
Data Index: 7722495 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9692. Min Range: -6.9692
Max Act: 6.6255. Min Act: -0.1700
Data Index: 1803388 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9692. Min Range: -6.9692
Max Act: 6.5942. Min Act: -0.1700
Data Index: 2331519 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9692. Min Range: -6.9692
Max Act: 6.5630. Min Act: -0.1700
Data Index: 5652745 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9692. Min Range: -6.9692
Max Act: 6.5317. Min Act: -0.1700
Data Index: 3483243 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9692. Min Range: -6.9692
Max Act: 6.5005. Min Act: -0.1700
Data Index: 7578395 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9692. Min Range: -6.9692
Max Act: 6.4380. Min Act: -0.1700
Data Index: 5937646 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9692. Min Range: -6.9692
Max Act: 6.4380. Min Act: -0.1700
Data Index: 6400303 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9692. Min Range: -6.9692
Max Act: 6.4067. Min Act: -0.1700
Data Index: 6400305 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9692. Min Range: -6.9692
Max Act: 6.4380. Min Act: -0.1700
Data Index: 911446 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9692. Min Range: -6.9692
Max Act: 6.4067. Min Act: -0.1700
Data Index: 6741493 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9692. Min Range: -6.9692
Max Act: 6.4067. Min Act: -0.1700
Data Index: 3045198 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9692. Min Range: -6.9692
Max Act: 6.4067. Min Act: -0.1700
Data Index: 6670815 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9692. Min Range: -6.9692
Max Act: 6.4067. Min Act: -0.1700
Data Index: 557909 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9692. Min Range: -6.9692
Max Act: 6.3755. Min Act: -0.1700
Data Index: 4416769 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19