Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2622 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0213. Min Range: -2.0213
Max Act: 2.0213. Min Act: -0.1700
Data Index: 4932392 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0213. Min Range: -2.0213
Max Act: 1.9367. Min Act: -0.1700
Data Index: 570186 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0213. Min Range: -2.0213
Max Act: 1.9197. Min Act: -0.1700
Data Index: 819527 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0213. Min Range: -2.0213
Max Act: 1.9367. Min Act: -0.1700
Data Index: 552411 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0213. Min Range: -2.0213
Max Act: 1.9026. Min Act: -0.1700
Data Index: 4635487 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0213. Min Range: -2.0213
Max Act: 1.9367. Min Act: -0.1700
Data Index: 6500421 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0213. Min Range: -2.0213
Max Act: 1.9197. Min Act: -0.1700
Data Index: 321341 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0213. Min Range: -2.0213
Max Act: 1.9197. Min Act: -0.1700
Data Index: 6430954 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0213. Min Range: -2.0213
Max Act: 1.9197. Min Act: -0.1700
Data Index: 6921652 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0213. Min Range: -2.0213
Max Act: 1.9026. Min Act: -0.1700
Data Index: 1638165 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0213. Min Range: -2.0213
Max Act: 1.9197. Min Act: -0.1700
Data Index: 5837144 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0213. Min Range: -2.0213
Max Act: 1.9197. Min Act: -0.1700
Data Index: 6344516 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0213. Min Range: -2.0213
Max Act: 1.8856. Min Act: -0.1700
Data Index: 7245863 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0213. Min Range: -2.0213
Max Act: 1.8685. Min Act: -0.1700
Data Index: 2507444 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0213. Min Range: -2.0213
Max Act: 1.8685. Min Act: -0.1700
Data Index: 4570756 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0213. Min Range: -2.0213
Max Act: 1.8856. Min Act: -0.1700
Data Index: 57781 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0213. Min Range: -2.0213
Max Act: 1.8685. Min Act: -0.1700
Data Index: 8646162 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0213. Min Range: -2.0213
Max Act: 1.8856. Min Act: -0.1700
Data Index: 6539088 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0213. Min Range: -2.0213
Max Act: 1.9026. Min Act: -0.1700
Data Index: 3606240 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0213. Min Range: -2.0213
Max Act: 1.8514. Min Act: -0.1700
Data Index: 3912430 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19