Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2249 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1295. Min Range: -5.1295
Max Act: 5.1295. Min Act: -0.1700
Data Index: 8757041 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1295. Min Range: -5.1295
Max Act: 5.0982. Min Act: -0.1700
Data Index: 4173530 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.8795. Min Act: -0.1700
Data Index: 6090556 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.8170. Min Act: -0.1700
Data Index: 6683554 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.8170. Min Act: -0.1700
Data Index: 112370 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.7545. Min Act: -0.1700
Data Index: 7100240 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.7232. Min Act: -0.1700
Data Index: 874678 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.7545. Min Act: -0.1700
Data Index: 785648 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.7232. Min Act: -0.1700
Data Index: 6511887 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.6920. Min Act: -0.1700
Data Index: 646679 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.6920. Min Act: -0.1700
Data Index: 2926267 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.6607. Min Act: -0.1700
Data Index: 4154818 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.6295. Min Act: -0.1700
Data Index: 4272181 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.6607. Min Act: -0.1700
Data Index: 994817 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.6607. Min Act: -0.1700
Data Index: 2602105 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.6920. Min Act: -0.1700
Data Index: 4404786 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.6295. Min Act: -0.1700
Data Index: 1427225 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.6295. Min Act: -0.1700
Data Index: 7413114 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.5982. Min Act: -0.1700
Data Index: 4473200 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.5982. Min Act: -0.1700
Data Index: 4856845 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19