Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5432 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4902. Min Range: -4.4902
Max Act: 4.4902. Min Act: -0.1700
Data Index: 845183 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4902. Min Range: -4.4902
Max Act: 4.4589. Min Act: -0.1700
Data Index: 5276124 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4902. Min Range: -4.4902
Max Act: 4.4277. Min Act: -0.1700
Data Index: 8104200 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4902. Min Range: -4.4902
Max Act: 4.3339. Min Act: -0.1700
Data Index: 8829285 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4902. Min Range: -4.4902
Max Act: 4.2714. Min Act: -0.1700
Data Index: 6849464 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4902. Min Range: -4.4902
Max Act: 4.3027. Min Act: -0.1700
Data Index: 4900225 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4902. Min Range: -4.4902
Max Act: 4.2402. Min Act: -0.1700
Data Index: 8684451 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4902. Min Range: -4.4902
Max Act: 4.2402. Min Act: -0.1700
Data Index: 2503556 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4902. Min Range: -4.4902
Max Act: 4.2402. Min Act: -0.1700
Data Index: 4889338 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4902. Min Range: -4.4902
Max Act: 4.2089. Min Act: -0.1700
Data Index: 796267 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4902. Min Range: -4.4902
Max Act: 4.2089. Min Act: -0.1700
Data Index: 2962702 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4902. Min Range: -4.4902
Max Act: 4.1777. Min Act: -0.1700
Data Index: 6050731 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4902. Min Range: -4.4902
Max Act: 4.1777. Min Act: -0.1700
Data Index: 8248896 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4902. Min Range: -4.4902
Max Act: 4.2089. Min Act: -0.1700
Data Index: 8477401 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4902. Min Range: -4.4902
Max Act: 4.1777. Min Act: -0.1700
Data Index: 3743460 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4902. Min Range: -4.4902
Max Act: 4.1464. Min Act: -0.1700
Data Index: 1606847 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4902. Min Range: -4.4902
Max Act: 4.1777. Min Act: -0.1700
Data Index: 1676789 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4902. Min Range: -4.4902
Max Act: 4.1464. Min Act: -0.1700
Data Index: 670580 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4902. Min Range: -4.4902
Max Act: 4.1464. Min Act: -0.1700
Data Index: 3834160 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4902. Min Range: -4.4902
Max Act: 4.1464. Min Act: -0.1700
Data Index: 5604662 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19