Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 116 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2243. Min Range: -3.2243
Max Act: 3.2243. Min Act: -0.1700
Data Index: 7114002 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2243. Min Range: -3.2243
Max Act: 3.2085. Min Act: -0.1700
Data Index: 1157140 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2243. Min Range: -3.2243
Max Act: 3.1771. Min Act: -0.1700
Data Index: 2395850 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2243. Min Range: -3.2243
Max Act: 3.1771. Min Act: -0.1700
Data Index: 2755252 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2243. Min Range: -3.2243
Max Act: 3.1771. Min Act: -0.1700
Data Index: 5328019 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2243. Min Range: -3.2243
Max Act: 3.1613. Min Act: -0.1700
Data Index: 8774126 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2243. Min Range: -3.2243
Max Act: 3.1456. Min Act: -0.1700
Data Index: 4111251 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2243. Min Range: -3.2243
Max Act: 3.1299. Min Act: -0.1700
Data Index: 2399185 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2243. Min Range: -3.2243
Max Act: 3.1299. Min Act: -0.1700
Data Index: 8793585 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2243. Min Range: -3.2243
Max Act: 3.1141. Min Act: -0.1700
Data Index: 2077220 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2243. Min Range: -3.2243
Max Act: 3.1141. Min Act: -0.1700
Data Index: 62039 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2243. Min Range: -3.2243
Max Act: 3.1299. Min Act: -0.1700
Data Index: 2359301 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2243. Min Range: -3.2243
Max Act: 3.0984. Min Act: -0.1700
Data Index: 4591238 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2243. Min Range: -3.2243
Max Act: 3.0826. Min Act: -0.1700
Data Index: 3199742 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2243. Min Range: -3.2243
Max Act: 3.0826. Min Act: -0.1700
Data Index: 468788 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2243. Min Range: -3.2243
Max Act: 3.0984. Min Act: -0.1700
Data Index: 6396509 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2243. Min Range: -3.2243
Max Act: 3.0668. Min Act: -0.1700
Data Index: 5494103 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2243. Min Range: -3.2243
Max Act: 3.0668. Min Act: -0.1700
Data Index: 7334742 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2243. Min Range: -3.2243
Max Act: 3.0826. Min Act: -0.1700
Data Index: 7633137 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2243. Min Range: -3.2243
Max Act: 3.0510. Min Act: -0.1700
Data Index: 70452 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19