Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 718 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4706. Min Range: -3.4706
Max Act: 3.4706. Min Act: -0.1700
Data Index: 4315025 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4706. Min Range: -3.4706
Max Act: 3.4393. Min Act: -0.1700
Data Index: 6040954 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4706. Min Range: -3.4706
Max Act: 3.4079. Min Act: -0.1700
Data Index: 7326550 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4706. Min Range: -3.4706
Max Act: 3.3766. Min Act: -0.1700
Data Index: 585798 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4706. Min Range: -3.4706
Max Act: 3.3452. Min Act: -0.1700
Data Index: 1167456 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4706. Min Range: -3.4706
Max Act: 3.3452. Min Act: -0.1700
Data Index: 5514618 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4706. Min Range: -3.4706
Max Act: 3.3452. Min Act: -0.1700
Data Index: 7418205 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4706. Min Range: -3.4706
Max Act: 3.3452. Min Act: -0.1700
Data Index: 1116035 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4706. Min Range: -3.4706
Max Act: 3.3452. Min Act: -0.1700
Data Index: 3895891 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4706. Min Range: -3.4706
Max Act: 3.3452. Min Act: -0.1700
Data Index: 1565969 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4706. Min Range: -3.4706
Max Act: 3.3452. Min Act: -0.1700
Data Index: 7541658 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4706. Min Range: -3.4706
Max Act: 3.3138. Min Act: -0.1700
Data Index: 8355740 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4706. Min Range: -3.4706
Max Act: 3.3138. Min Act: -0.1700
Data Index: 7421181 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4706. Min Range: -3.4706
Max Act: 3.3138. Min Act: -0.1700
Data Index: 2014624 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4706. Min Range: -3.4706
Max Act: 3.3138. Min Act: -0.1700
Data Index: 3591463 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4706. Min Range: -3.4706
Max Act: 3.3138. Min Act: -0.1700
Data Index: 7708808 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4706. Min Range: -3.4706
Max Act: 3.3138. Min Act: -0.1700
Data Index: 7140385 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4706. Min Range: -3.4706
Max Act: 3.3138. Min Act: -0.1700
Data Index: 5948468 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4706. Min Range: -3.4706
Max Act: 3.2981. Min Act: -0.1700
Data Index: 436901 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4706. Min Range: -3.4706
Max Act: 3.2824. Min Act: -0.1700
Data Index: 1010358 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19