Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2918 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9652. Min Range: -4.9652
Max Act: 4.9652. Min Act: -0.1700
Data Index: 2249188 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9652. Min Range: -4.9652
Max Act: 4.8402. Min Act: -0.1700
Data Index: 1888221 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9652. Min Range: -4.9652
Max Act: 4.8089. Min Act: -0.1700
Data Index: 4014436 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9652. Min Range: -4.9652
Max Act: 4.7777. Min Act: -0.1700
Data Index: 5588274 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9652. Min Range: -4.9652
Max Act: 4.7464. Min Act: -0.1700
Data Index: 7497470 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9652. Min Range: -4.9652
Max Act: 4.7464. Min Act: -0.1700
Data Index: 4253055 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9652. Min Range: -4.9652
Max Act: 4.7464. Min Act: -0.1700
Data Index: 3200800 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9652. Min Range: -4.9652
Max Act: 4.7464. Min Act: -0.1700
Data Index: 4718135 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9652. Min Range: -4.9652
Max Act: 4.7464. Min Act: -0.1700
Data Index: 7233742 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9652. Min Range: -4.9652
Max Act: 4.7464. Min Act: -0.1700
Data Index: 5408018 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9652. Min Range: -4.9652
Max Act: 4.7152. Min Act: -0.1700
Data Index: 8355839 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9652. Min Range: -4.9652
Max Act: 4.7152. Min Act: -0.1700
Data Index: 2050831 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9652. Min Range: -4.9652
Max Act: 4.7152. Min Act: -0.1700
Data Index: 21242 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9652. Min Range: -4.9652
Max Act: 4.6839. Min Act: -0.1700
Data Index: 3669775 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9652. Min Range: -4.9652
Max Act: 4.6527. Min Act: -0.1700
Data Index: 4357482 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9652. Min Range: -4.9652
Max Act: 4.6839. Min Act: -0.1700
Data Index: 733251 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9652. Min Range: -4.9652
Max Act: 4.6839. Min Act: -0.1700
Data Index: 5270000 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9652. Min Range: -4.9652
Max Act: 4.6214. Min Act: -0.1700
Data Index: 5594478 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9652. Min Range: -4.9652
Max Act: 4.6214. Min Act: -0.1700
Data Index: 605107 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9652. Min Range: -4.9652
Max Act: 4.6214. Min Act: -0.1700
Data Index: 804796 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19