Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6140 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5583. Min Range: -7.5583
Max Act: 7.5583. Min Act: -0.1700
Data Index: 69596 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5583. Min Range: -7.5583
Max Act: 7.2770. Min Act: -0.1700
Data Index: 860999 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5583. Min Range: -7.5583
Max Act: 7.2145. Min Act: -0.1700
Data Index: 693283 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5583. Min Range: -7.5583
Max Act: 7.0270. Min Act: -0.1700
Data Index: 1834450 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5583. Min Range: -7.5583
Max Act: 7.0270. Min Act: -0.1700
Data Index: 6151172 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5583. Min Range: -7.5583
Max Act: 6.9958. Min Act: -0.1700
Data Index: 5364823 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5583. Min Range: -7.5583
Max Act: 6.9020. Min Act: -0.1700
Data Index: 4095830 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5583. Min Range: -7.5583
Max Act: 6.8708. Min Act: -0.1700
Data Index: 3977449 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5583. Min Range: -7.5583
Max Act: 6.8395. Min Act: -0.1700
Data Index: 2753123 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5583. Min Range: -7.5583
Max Act: 6.8708. Min Act: -0.1700
Data Index: 3398191 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5583. Min Range: -7.5583
Max Act: 6.8395. Min Act: -0.1700
Data Index: 619772 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5583. Min Range: -7.5583
Max Act: 6.8395. Min Act: -0.1700
Data Index: 6664485 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5583. Min Range: -7.5583
Max Act: 6.8395. Min Act: -0.1700
Data Index: 3566335 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5583. Min Range: -7.5583
Max Act: 6.8083. Min Act: -0.1700
Data Index: 7648957 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5583. Min Range: -7.5583
Max Act: 6.7770. Min Act: -0.1700
Data Index: 1635369 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5583. Min Range: -7.5583
Max Act: 6.8083. Min Act: -0.1700
Data Index: 2194825 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5583. Min Range: -7.5583
Max Act: 6.8083. Min Act: -0.1700
Data Index: 4572872 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5583. Min Range: -7.5583
Max Act: 6.8083. Min Act: -0.1700
Data Index: 1230259 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5583. Min Range: -7.5583
Max Act: 6.7770. Min Act: -0.1700
Data Index: 2646744 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5583. Min Range: -7.5583
Max Act: 6.7458. Min Act: -0.1700
Data Index: 705009 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19