Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2833 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0672. Min Range: -7.0672
Max Act: 7.0672. Min Act: -0.1700
Data Index: 1036760 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0672. Min Range: -7.0672
Max Act: 6.7234. Min Act: -0.1700
Data Index: 2339820 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0672. Min Range: -7.0672
Max Act: 6.7234. Min Act: -0.1700
Data Index: 1906671 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0672. Min Range: -7.0672
Max Act: 6.6922. Min Act: -0.1700
Data Index: 4932112 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0672. Min Range: -7.0672
Max Act: 6.6609. Min Act: -0.1700
Data Index: 8573364 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0672. Min Range: -7.0672
Max Act: 6.5672. Min Act: -0.1700
Data Index: 915182 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0672. Min Range: -7.0672
Max Act: 6.5359. Min Act: -0.1700
Data Index: 8634115 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0672. Min Range: -7.0672
Max Act: 6.5359. Min Act: -0.1700
Data Index: 3716789 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0672. Min Range: -7.0672
Max Act: 6.4734. Min Act: -0.1700
Data Index: 272422 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0672. Min Range: -7.0672
Max Act: 6.4734. Min Act: -0.1700
Data Index: 4511316 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0672. Min Range: -7.0672
Max Act: 6.4422. Min Act: -0.1700
Data Index: 4428971 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0672. Min Range: -7.0672
Max Act: 6.4422. Min Act: -0.1700
Data Index: 1005585 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0672. Min Range: -7.0672
Max Act: 6.3797. Min Act: -0.1700
Data Index: 1808642 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0672. Min Range: -7.0672
Max Act: 6.3484. Min Act: -0.1700
Data Index: 5504529 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0672. Min Range: -7.0672
Max Act: 6.3484. Min Act: -0.1700
Data Index: 606753 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0672. Min Range: -7.0672
Max Act: 6.3484. Min Act: -0.1700
Data Index: 7472536 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0672. Min Range: -7.0672
Max Act: 6.3484. Min Act: -0.1700
Data Index: 4718247 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0672. Min Range: -7.0672
Max Act: 6.3484. Min Act: -0.1700
Data Index: 655415 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0672. Min Range: -7.0672
Max Act: 6.3484. Min Act: -0.1700
Data Index: 3110303 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0672. Min Range: -7.0672
Max Act: 6.3172. Min Act: -0.1700
Data Index: 1909471 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19