Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2985 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5264. Min Range: -5.5264
Max Act: 5.5264. Min Act: -0.1700
Data Index: 6135785 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5264. Min Range: -5.5264
Max Act: 5.4951. Min Act: -0.1700
Data Index: 4530911 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5264. Min Range: -5.5264
Max Act: 5.3701. Min Act: -0.1700
Data Index: 4473075 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5264. Min Range: -5.5264
Max Act: 5.3701. Min Act: -0.1700
Data Index: 7765630 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5264. Min Range: -5.5264
Max Act: 5.2764. Min Act: -0.1700
Data Index: 2711393 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5264. Min Range: -5.5264
Max Act: 5.2764. Min Act: -0.1700
Data Index: 4971123 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5264. Min Range: -5.5264
Max Act: 5.2451. Min Act: -0.1700
Data Index: 2237028 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5264. Min Range: -5.5264
Max Act: 5.2139. Min Act: -0.1700
Data Index: 2237035 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5264. Min Range: -5.5264
Max Act: 5.2139. Min Act: -0.1700
Data Index: 8665256 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5264. Min Range: -5.5264
Max Act: 5.2139. Min Act: -0.1700
Data Index: 2730060 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5264. Min Range: -5.5264
Max Act: 5.2139. Min Act: -0.1700
Data Index: 8463518 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5264. Min Range: -5.5264
Max Act: 5.1826. Min Act: -0.1700
Data Index: 5261636 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5264. Min Range: -5.5264
Max Act: 5.1826. Min Act: -0.1700
Data Index: 5765437 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5264. Min Range: -5.5264
Max Act: 5.1514. Min Act: -0.1700
Data Index: 1661695 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5264. Min Range: -5.5264
Max Act: 5.1514. Min Act: -0.1700
Data Index: 1897737 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5264. Min Range: -5.5264
Max Act: 5.1201. Min Act: -0.1700
Data Index: 3648215 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5264. Min Range: -5.5264
Max Act: 5.1201. Min Act: -0.1700
Data Index: 3859224 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5264. Min Range: -5.5264
Max Act: 5.1201. Min Act: -0.1700
Data Index: 7573604 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5264. Min Range: -5.5264
Max Act: 5.1201. Min Act: -0.1700
Data Index: 2330782 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5264. Min Range: -5.5264
Max Act: 5.1201. Min Act: -0.1700
Data Index: 1290275 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19