Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2456 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4314. Min Range: -3.4314
Max Act: 3.4314. Min Act: -0.1700
Data Index: 5353506 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4314. Min Range: -3.4314
Max Act: 3.4157. Min Act: -0.1700
Data Index: 3801352 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4314. Min Range: -3.4314
Max Act: 3.4157. Min Act: -0.1700
Data Index: 7290848 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4314. Min Range: -3.4314
Max Act: 3.3844. Min Act: -0.1700
Data Index: 1862211 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4314. Min Range: -3.4314
Max Act: 3.4000. Min Act: -0.1700
Data Index: 5485008 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4314. Min Range: -3.4314
Max Act: 3.4000. Min Act: -0.1700
Data Index: 3815913 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4314. Min Range: -3.4314
Max Act: 3.3530. Min Act: -0.1700
Data Index: 1218070 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4314. Min Range: -3.4314
Max Act: 3.3530. Min Act: -0.1700
Data Index: 2410393 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4314. Min Range: -3.4314
Max Act: 3.3216. Min Act: -0.1700
Data Index: 1677093 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4314. Min Range: -3.4314
Max Act: 3.3059. Min Act: -0.1700
Data Index: 8224307 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4314. Min Range: -3.4314
Max Act: 3.2745. Min Act: -0.1700
Data Index: 3080846 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4314. Min Range: -3.4314
Max Act: 3.2902. Min Act: -0.1700
Data Index: 708436 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4314. Min Range: -3.4314
Max Act: 3.2745. Min Act: -0.1700
Data Index: 840656 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4314. Min Range: -3.4314
Max Act: 3.2902. Min Act: -0.1700
Data Index: 5170035 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4314. Min Range: -3.4314
Max Act: 3.2745. Min Act: -0.1700
Data Index: 8496796 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4314. Min Range: -3.4314
Max Act: 3.2745. Min Act: -0.1700
Data Index: 5647382 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4314. Min Range: -3.4314
Max Act: 3.2902. Min Act: -0.1700
Data Index: 4726540 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4314. Min Range: -3.4314
Max Act: 3.2745. Min Act: -0.1700
Data Index: 1729154 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4314. Min Range: -3.4314
Max Act: 3.2588. Min Act: -0.1700
Data Index: 2133049 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4314. Min Range: -3.4314
Max Act: 3.2588. Min Act: -0.1700
Data Index: 3817648 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19