Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3025 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.5633. Min Act: -0.1700
Data Index: 712075 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.5320. Min Act: -0.1700
Data Index: 5663273 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.4695. Min Act: -0.1700
Data Index: 6612366 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.4695. Min Act: -0.1700
Data Index: 6057442 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.4383. Min Act: -0.1700
Data Index: 2572614 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.4070. Min Act: -0.1700
Data Index: 731092 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.4070. Min Act: -0.1699
Data Index: 8143383 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.3758. Min Act: -0.1700
Data Index: 3350830 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.3758. Min Act: -0.1700
Data Index: 3884288 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.3758. Min Act: -0.1700
Data Index: 1085028 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.3758. Min Act: -0.1700
Data Index: 7713928 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.3445. Min Act: -0.1700
Data Index: 7844537 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.3445. Min Act: -0.1700
Data Index: 8667662 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.3133. Min Act: -0.1700
Data Index: 1261299 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.2820. Min Act: -0.1700
Data Index: 4432488 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.2820. Min Act: -0.1700
Data Index: 6308875 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.2820. Min Act: -0.1700
Data Index: 8119874 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.2508. Min Act: -0.1700
Data Index: 4535152 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.2820. Min Act: -0.1700
Data Index: 8023265 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.2195. Min Act: -0.1700
Data Index: 3258382 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19