Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1076 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5754. Min Range: -5.5754
Max Act: 5.5754. Min Act: -0.1700
Data Index: 6404633 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5754. Min Range: -5.5754
Max Act: 5.3567. Min Act: -0.1700
Data Index: 1213043 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5754. Min Range: -5.5754
Max Act: 5.2629. Min Act: -0.1700
Data Index: 5278648 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5754. Min Range: -5.5754
Max Act: 5.2629. Min Act: -0.1700
Data Index: 4665538 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5754. Min Range: -5.5754
Max Act: 5.2629. Min Act: -0.1700
Data Index: 2751842 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5754. Min Range: -5.5754
Max Act: 5.2629. Min Act: -0.1700
Data Index: 3375070 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5754. Min Range: -5.5754
Max Act: 5.2004. Min Act: -0.1700
Data Index: 4530414 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5754. Min Range: -5.5754
Max Act: 5.2004. Min Act: -0.1700
Data Index: 5038411 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5754. Min Range: -5.5754
Max Act: 5.2004. Min Act: -0.1700
Data Index: 3018211 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5754. Min Range: -5.5754
Max Act: 5.1379. Min Act: -0.1700
Data Index: 2380750 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5754. Min Range: -5.5754
Max Act: 5.1379. Min Act: -0.1700
Data Index: 4046344 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5754. Min Range: -5.5754
Max Act: 5.1379. Min Act: -0.1700
Data Index: 905423 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5754. Min Range: -5.5754
Max Act: 5.1067. Min Act: -0.1700
Data Index: 8089362 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5754. Min Range: -5.5754
Max Act: 5.1067. Min Act: -0.1700
Data Index: 2647619 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5754. Min Range: -5.5754
Max Act: 5.0754. Min Act: -0.1700
Data Index: 8325726 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5754. Min Range: -5.5754
Max Act: 5.0754. Min Act: -0.1700
Data Index: 3065387 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5754. Min Range: -5.5754
Max Act: 5.0754. Min Act: -0.1700
Data Index: 8407955 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5754. Min Range: -5.5754
Max Act: 5.0442. Min Act: -0.1700
Data Index: 6370789 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5754. Min Range: -5.5754
Max Act: 5.0442. Min Act: -0.1700
Data Index: 2475711 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5754. Min Range: -5.5754
Max Act: 5.0442. Min Act: -0.1700
Data Index: 4902053 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19