Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4013 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0097. Min Range: -6.0097
Max Act: 6.0097. Min Act: -0.1700
Data Index: 1879421 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.9472. Min Act: -0.1700
Data Index: 428603 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.8847. Min Act: -0.1700
Data Index: 660979 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.8222. Min Act: -0.1700
Data Index: 7033423 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.7284. Min Act: -0.1700
Data Index: 4607438 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.6972. Min Act: -0.1700
Data Index: 3884932 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.6659. Min Act: -0.1700
Data Index: 4700377 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.6659. Min Act: -0.1700
Data Index: 6717091 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.6347. Min Act: -0.1700
Data Index: 7058871 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.6347. Min Act: -0.1700
Data Index: 2322618 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.6347. Min Act: -0.1700
Data Index: 2763208 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.6347. Min Act: -0.1700
Data Index: 1024600 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.6347. Min Act: -0.1700
Data Index: 8511332 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.6034. Min Act: -0.1700
Data Index: 5235358 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.6034. Min Act: -0.1700
Data Index: 2558478 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.6034. Min Act: -0.1700
Data Index: 6034056 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.6034. Min Act: -0.1700
Data Index: 2518612 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.5722. Min Act: -0.1700
Data Index: 1970359 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.5409. Min Act: -0.1700
Data Index: 5235357 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.5722. Min Act: -0.1700
Data Index: 1911859 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19