Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1327 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.3652. Min Range: -4.3652
Max Act: 4.3652. Min Act: -0.1700
Data Index: 3694397 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3652. Min Range: -4.3652
Max Act: 4.2715. Min Act: -0.1700
Data Index: 3134953 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3652. Min Range: -4.3652
Max Act: 4.2402. Min Act: -0.1700
Data Index: 1407390 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3652. Min Range: -4.3652
Max Act: 4.2402. Min Act: -0.1700
Data Index: 5740196 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3652. Min Range: -4.3652
Max Act: 4.2402. Min Act: -0.1700
Data Index: 355987 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3652. Min Range: -4.3652
Max Act: 4.1777. Min Act: -0.1700
Data Index: 2886048 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3652. Min Range: -4.3652
Max Act: 4.1777. Min Act: -0.1700
Data Index: 6642457 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3652. Min Range: -4.3652
Max Act: 4.1465. Min Act: -0.1700
Data Index: 3403017 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3652. Min Range: -4.3652
Max Act: 4.1152. Min Act: -0.1700
Data Index: 4761509 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3652. Min Range: -4.3652
Max Act: 4.1465. Min Act: -0.1700
Data Index: 5942636 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3652. Min Range: -4.3652
Max Act: 4.1465. Min Act: -0.1700
Data Index: 2876118 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3652. Min Range: -4.3652
Max Act: 4.1465. Min Act: -0.1700
Data Index: 1959391 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3652. Min Range: -4.3652
Max Act: 4.1465. Min Act: -0.1700
Data Index: 3723916 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3652. Min Range: -4.3652
Max Act: 4.1152. Min Act: -0.1700
Data Index: 5799110 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3652. Min Range: -4.3652
Max Act: 4.1152. Min Act: -0.1700
Data Index: 3845602 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3652. Min Range: -4.3652
Max Act: 4.1152. Min Act: -0.1700
Data Index: 3923175 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3652. Min Range: -4.3652
Max Act: 4.1152. Min Act: -0.1700
Data Index: 1810810 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3652. Min Range: -4.3652
Max Act: 4.1152. Min Act: -0.1700
Data Index: 5381420 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3652. Min Range: -4.3652
Max Act: 4.1465. Min Act: -0.1700
Data Index: 3562524 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3652. Min Range: -4.3652
Max Act: 4.0840. Min Act: -0.1700
Data Index: 3692489 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19