Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5041 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2125. Min Range: -3.2125
Max Act: 3.2125. Min Act: -0.1700
Data Index: 2737400 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2125. Min Range: -3.2125
Max Act: 3.1339. Min Act: -0.1700
Data Index: 7821806 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2125. Min Range: -3.2125
Max Act: 3.1181. Min Act: -0.1700
Data Index: 8197919 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2125. Min Range: -3.2125
Max Act: 3.1024. Min Act: -0.1700
Data Index: 7769733 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2125. Min Range: -3.2125
Max Act: 3.0866. Min Act: -0.1700
Data Index: 4210598 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2125. Min Range: -3.2125
Max Act: 3.0708. Min Act: -0.1700
Data Index: 2175092 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2125. Min Range: -3.2125
Max Act: 3.0551. Min Act: -0.1700
Data Index: 7912110 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2125. Min Range: -3.2125
Max Act: 3.0393. Min Act: -0.1700
Data Index: 5135176 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2125. Min Range: -3.2125
Max Act: 3.0235. Min Act: -0.1700
Data Index: 3088545 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2125. Min Range: -3.2125
Max Act: 3.0235. Min Act: -0.1700
Data Index: 5829570 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2125. Min Range: -3.2125
Max Act: 3.0235. Min Act: -0.1700
Data Index: 702548 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2125. Min Range: -3.2125
Max Act: 2.9761. Min Act: -0.1700
Data Index: 4484902 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2125. Min Range: -3.2125
Max Act: 2.9919. Min Act: -0.1700
Data Index: 1721067 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2125. Min Range: -3.2125
Max Act: 2.9919. Min Act: -0.1700
Data Index: 3590855 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2125. Min Range: -3.2125
Max Act: 2.9919. Min Act: -0.1700
Data Index: 5057810 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2125. Min Range: -3.2125
Max Act: 3.0077. Min Act: -0.1700
Data Index: 2455146 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2125. Min Range: -3.2125
Max Act: 2.9761. Min Act: -0.1700
Data Index: 5912324 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2125. Min Range: -3.2125
Max Act: 2.9602. Min Act: -0.1700
Data Index: 6412527 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2125. Min Range: -3.2125
Max Act: 2.9761. Min Act: -0.1700
Data Index: 5835062 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2125. Min Range: -3.2125
Max Act: 2.9602. Min Act: -0.1700
Data Index: 4951713 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19