Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5570 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7588. Min Range: -5.7588
Max Act: 5.7588. Min Act: -0.1700
Data Index: 6008881 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7588. Min Range: -5.7588
Max Act: 5.7588. Min Act: -0.1700
Data Index: 6008889 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7588. Min Range: -5.7588
Max Act: 5.7276. Min Act: -0.1700
Data Index: 284388 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7588. Min Range: -5.7588
Max Act: 5.7276. Min Act: -0.1700
Data Index: 7527767 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7588. Min Range: -5.7588
Max Act: 5.6026. Min Act: -0.1700
Data Index: 759923 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7588. Min Range: -5.7588
Max Act: 5.4776. Min Act: -0.1700
Data Index: 873366 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7588. Min Range: -5.7588
Max Act: 5.4776. Min Act: -0.1700
Data Index: 2026135 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7588. Min Range: -5.7588
Max Act: 5.3838. Min Act: -0.1700
Data Index: 4678862 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7588. Min Range: -5.7588
Max Act: 5.3838. Min Act: -0.1700
Data Index: 5833811 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7588. Min Range: -5.7588
Max Act: 5.3526. Min Act: -0.1700
Data Index: 356579 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7588. Min Range: -5.7588
Max Act: 5.3213. Min Act: -0.1700
Data Index: 6577996 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7588. Min Range: -5.7588
Max Act: 5.2901. Min Act: -0.1700
Data Index: 865273 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7588. Min Range: -5.7588
Max Act: 5.3213. Min Act: -0.1700
Data Index: 913371 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7588. Min Range: -5.7588
Max Act: 5.2901. Min Act: -0.1700
Data Index: 3576119 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7588. Min Range: -5.7588
Max Act: 5.2901. Min Act: -0.1700
Data Index: 2832484 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7588. Min Range: -5.7588
Max Act: 5.2901. Min Act: -0.1700
Data Index: 269483 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7588. Min Range: -5.7588
Max Act: 5.2901. Min Act: -0.1700
Data Index: 5612329 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7588. Min Range: -5.7588
Max Act: 5.2901. Min Act: -0.1700
Data Index: 7051642 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7588. Min Range: -5.7588
Max Act: 5.2901. Min Act: -0.1700
Data Index: 287399 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7588. Min Range: -5.7588
Max Act: 5.2588. Min Act: -0.1700
Data Index: 1335535 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19