Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3795 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4760. Min Range: -3.4760
Max Act: 3.4760. Min Act: -0.1700
Data Index: 5804173 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4760. Min Range: -3.4760
Max Act: 3.4447. Min Act: -0.1700
Data Index: 1428842 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4760. Min Range: -3.4760
Max Act: 3.4133. Min Act: -0.1700
Data Index: 4366964 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4760. Min Range: -3.4760
Max Act: 3.3820. Min Act: -0.1700
Data Index: 65980 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4760. Min Range: -3.4760
Max Act: 3.3506. Min Act: -0.1700
Data Index: 8377291 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4760. Min Range: -3.4760
Max Act: 3.3349. Min Act: -0.1700
Data Index: 4581960 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4760. Min Range: -3.4760
Max Act: 3.3192. Min Act: -0.1700
Data Index: 2125659 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4760. Min Range: -3.4760
Max Act: 3.3349. Min Act: -0.1700
Data Index: 5377237 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4760. Min Range: -3.4760
Max Act: 3.3192. Min Act: -0.1700
Data Index: 3498620 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4760. Min Range: -3.4760
Max Act: 3.3349. Min Act: -0.1700
Data Index: 2240652 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4760. Min Range: -3.4760
Max Act: 3.3192. Min Act: -0.1700
Data Index: 2240656 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4760. Min Range: -3.4760
Max Act: 3.3349. Min Act: -0.1700
Data Index: 7007541 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4760. Min Range: -3.4760
Max Act: 3.2878. Min Act: -0.1700
Data Index: 6743952 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4760. Min Range: -3.4760
Max Act: 3.3192. Min Act: -0.1700
Data Index: 4364844 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4760. Min Range: -3.4760
Max Act: 3.3035. Min Act: -0.1700
Data Index: 977756 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4760. Min Range: -3.4760
Max Act: 3.2721. Min Act: -0.1700
Data Index: 4095440 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4760. Min Range: -3.4760
Max Act: 3.2878. Min Act: -0.1700
Data Index: 6708272 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4760. Min Range: -3.4760
Max Act: 3.2878. Min Act: -0.1700
Data Index: 6915111 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4760. Min Range: -3.4760
Max Act: 3.2878. Min Act: -0.1700
Data Index: 5453378 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4760. Min Range: -3.4760
Max Act: 3.3035. Min Act: -0.1700
Data Index: 4588058 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19