Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2689 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7159. Min Range: -2.7159
Max Act: 2.7159. Min Act: -0.1700
Data Index: 970361 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7159. Min Range: -2.7159
Max Act: 2.6197. Min Act: -0.1700
Data Index: 868187 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7159. Min Range: -2.7159
Max Act: 2.6036. Min Act: -0.1700
Data Index: 7085211 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7159. Min Range: -2.7159
Max Act: 2.5875. Min Act: -0.1700
Data Index: 4023895 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7159. Min Range: -2.7159
Max Act: 2.5714. Min Act: -0.1700
Data Index: 109845 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7159. Min Range: -2.7159
Max Act: 2.5875. Min Act: -0.1700
Data Index: 2795623 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7159. Min Range: -2.7159
Max Act: 2.5553. Min Act: -0.1700
Data Index: 7425143 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7159. Min Range: -2.7159
Max Act: 2.5391. Min Act: -0.1700
Data Index: 311062 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7159. Min Range: -2.7159
Max Act: 2.5391. Min Act: -0.1700
Data Index: 3000876 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7159. Min Range: -2.7159
Max Act: 2.5391. Min Act: -0.1700
Data Index: 5380790 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7159. Min Range: -2.7159
Max Act: 2.5391. Min Act: -0.1700
Data Index: 7972233 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7159. Min Range: -2.7159
Max Act: 2.5391. Min Act: -0.1700
Data Index: 3092134 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7159. Min Range: -2.7159
Max Act: 2.5229. Min Act: -0.1700
Data Index: 7227961 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7159. Min Range: -2.7159
Max Act: 2.5068. Min Act: -0.1700
Data Index: 1815695 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7159. Min Range: -2.7159
Max Act: 2.5229. Min Act: -0.1700
Data Index: 7227963 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7159. Min Range: -2.7159
Max Act: 2.5068. Min Act: -0.1700
Data Index: 3834943 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7159. Min Range: -2.7159
Max Act: 2.5229. Min Act: -0.1700
Data Index: 1584357 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7159. Min Range: -2.7159
Max Act: 2.5229. Min Act: -0.1700
Data Index: 1590886 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7159. Min Range: -2.7159
Max Act: 2.5391. Min Act: -0.1700
Data Index: 5522897 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7159. Min Range: -2.7159
Max Act: 2.5229. Min Act: -0.1700
Data Index: 446820 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #19