Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4702 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9403. Min Range: -3.9403
Max Act: 3.9403. Min Act: -0.1700
Data Index: 1370399 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9403. Min Range: -3.9403
Max Act: 3.8152. Min Act: -0.1700
Data Index: 8679120 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9403. Min Range: -3.9403
Max Act: 3.8465. Min Act: -0.1700
Data Index: 2191914 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9403. Min Range: -3.9403
Max Act: 3.7840. Min Act: -0.1700
Data Index: 1860465 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9403. Min Range: -3.9403
Max Act: 3.7840. Min Act: -0.1700
Data Index: 1109442 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9403. Min Range: -3.9403
Max Act: 3.7214. Min Act: -0.1700
Data Index: 4921094 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9403. Min Range: -3.9403
Max Act: 3.7527. Min Act: -0.1700
Data Index: 2179009 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9403. Min Range: -3.9403
Max Act: 3.7527. Min Act: -0.1700
Data Index: 3368541 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9403. Min Range: -3.9403
Max Act: 3.7527. Min Act: -0.1700
Data Index: 6971050 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9403. Min Range: -3.9403
Max Act: 3.7527. Min Act: -0.1700
Data Index: 6214613 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9403. Min Range: -3.9403
Max Act: 3.7527. Min Act: -0.1700
Data Index: 6110522 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9403. Min Range: -3.9403
Max Act: 3.7527. Min Act: -0.1700
Data Index: 8633419 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9403. Min Range: -3.9403
Max Act: 3.7527. Min Act: -0.1700
Data Index: 5997009 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9403. Min Range: -3.9403
Max Act: 3.7527. Min Act: -0.1700
Data Index: 4835403 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9403. Min Range: -3.9403
Max Act: 3.7527. Min Act: -0.1700
Data Index: 2681274 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9403. Min Range: -3.9403
Max Act: 3.7214. Min Act: -0.1700
Data Index: 7491712 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9403. Min Range: -3.9403
Max Act: 3.7214. Min Act: -0.1700
Data Index: 6430373 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9403. Min Range: -3.9403
Max Act: 3.7214. Min Act: -0.1700
Data Index: 6485657 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9403. Min Range: -3.9403
Max Act: 3.6901. Min Act: -0.1700
Data Index: 5154225 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9403. Min Range: -3.9403
Max Act: 3.7214. Min Act: -0.1700
Data Index: 6706526 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19