Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5487 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1121. Min Range: -6.1121
Max Act: 6.1121. Min Act: -0.1700
Data Index: 5634248 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1121. Min Range: -6.1121
Max Act: 6.0496. Min Act: -0.1700
Data Index: 4915279 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.8934. Min Act: -0.1700
Data Index: 3523313 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.8621. Min Act: -0.1700
Data Index: 3755395 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.8621. Min Act: -0.1700
Data Index: 3915288 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.8309. Min Act: -0.1700
Data Index: 3491420 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.7996. Min Act: -0.1700
Data Index: 4529980 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.7371. Min Act: -0.1700
Data Index: 1023367 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.7371. Min Act: -0.1700
Data Index: 8767186 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.7059. Min Act: -0.1700
Data Index: 1472886 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.6746. Min Act: -0.1700
Data Index: 8824589 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.6434. Min Act: -0.1700
Data Index: 4825442 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.6121. Min Act: -0.1700
Data Index: 1324123 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.6121. Min Act: -0.1700
Data Index: 626473 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.5809. Min Act: -0.1700
Data Index: 6392018 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.5809. Min Act: -0.1700
Data Index: 798296 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.5496. Min Act: -0.1700
Data Index: 1148219 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.6121. Min Act: -0.1700
Data Index: 3004022 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.5496. Min Act: -0.1700
Data Index: 8110973 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.5809. Min Act: -0.1700
Data Index: 768610 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19