Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3184 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9396. Min Range: -3.9396
Max Act: 3.9396. Min Act: -0.1700
Data Index: 3374629 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9396. Min Range: -3.9396
Max Act: 3.6581. Min Act: -0.1700
Data Index: 456924 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9396. Min Range: -3.9396
Max Act: 3.7207. Min Act: -0.1700
Data Index: 3683214 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9396. Min Range: -3.9396
Max Act: 3.6581. Min Act: -0.1700
Data Index: 6848793 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9396. Min Range: -3.9396
Max Act: 3.5956. Min Act: -0.1700
Data Index: 4396302 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9396. Min Range: -3.9396
Max Act: 3.5956. Min Act: -0.1700
Data Index: 848369 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9396. Min Range: -3.9396
Max Act: 3.5956. Min Act: -0.1700
Data Index: 5459511 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9396. Min Range: -3.9396
Max Act: 3.5956. Min Act: -0.1700
Data Index: 224487 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9396. Min Range: -3.9396
Max Act: 3.5956. Min Act: -0.1700
Data Index: 5661721 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9396. Min Range: -3.9396
Max Act: 3.5642. Min Act: -0.1700
Data Index: 3293801 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9396. Min Range: -3.9396
Max Act: 3.5642. Min Act: -0.1700
Data Index: 2780772 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9396. Min Range: -3.9396
Max Act: 3.5642. Min Act: -0.1700
Data Index: 8297498 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9396. Min Range: -3.9396
Max Act: 3.5329. Min Act: -0.1700
Data Index: 3001226 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9396. Min Range: -3.9396
Max Act: 3.5329. Min Act: -0.1700
Data Index: 3327351 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9396. Min Range: -3.9396
Max Act: 3.5329. Min Act: -0.1700
Data Index: 1493787 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9396. Min Range: -3.9396
Max Act: 3.5329. Min Act: -0.1700
Data Index: 5009736 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9396. Min Range: -3.9396
Max Act: 3.5329. Min Act: -0.1700
Data Index: 4099716 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9396. Min Range: -3.9396
Max Act: 3.5329. Min Act: -0.1700
Data Index: 2696158 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9396. Min Range: -3.9396
Max Act: 3.5016. Min Act: -0.1700
Data Index: 6005939 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9396. Min Range: -3.9396
Max Act: 3.5016. Min Act: -0.1700
Data Index: 6395676 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19