Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 684 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.7310. Min Act: -0.1700
Data Index: 8716845 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.6997. Min Act: -0.1700
Data Index: 8716822 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.5747. Min Act: -0.1700
Data Index: 5253770 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.5747. Min Act: -0.1700
Data Index: 6506013 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.5747. Min Act: -0.1700
Data Index: 4375731 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.5435. Min Act: -0.1700
Data Index: 5914983 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.4810. Min Act: -0.1700
Data Index: 4375752 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.4497. Min Act: -0.1700
Data Index: 645605 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.4497. Min Act: -0.1700
Data Index: 2982001 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.4185. Min Act: -0.1700
Data Index: 7342797 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.4497. Min Act: -0.1700
Data Index: 1796089 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.4497. Min Act: -0.1700
Data Index: 4468318 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.4185. Min Act: -0.1700
Data Index: 5480444 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.4185. Min Act: -0.1700
Data Index: 4375745 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.3872. Min Act: -0.1700
Data Index: 5251271 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.3872. Min Act: -0.1700
Data Index: 5534636 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.3872. Min Act: -0.1700
Data Index: 4948396 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.3872. Min Act: -0.1700
Data Index: 2551194 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.3872. Min Act: -0.1700
Data Index: 3589801 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.3872. Min Act: -0.1700
Data Index: 1463240 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19