Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2350 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4405. Min Range: -7.4405
Max Act: 7.4405. Min Act: -0.1700
Data Index: 4452443 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4405. Min Range: -7.4405
Max Act: 7.2842. Min Act: -0.1700
Data Index: 6422670 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4405. Min Range: -7.4405
Max Act: 7.2530. Min Act: -0.1700
Data Index: 4340297 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4405. Min Range: -7.4405
Max Act: 7.2217. Min Act: -0.1700
Data Index: 8378309 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4405. Min Range: -7.4405
Max Act: 7.2217. Min Act: -0.1700
Data Index: 5004077 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4405. Min Range: -7.4405
Max Act: 7.2530. Min Act: -0.1700
Data Index: 939011 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4405. Min Range: -7.4405
Max Act: 7.2217. Min Act: -0.1700
Data Index: 7900999 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4405. Min Range: -7.4405
Max Act: 7.2217. Min Act: -0.1700
Data Index: 5709819 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4405. Min Range: -7.4405
Max Act: 7.1592. Min Act: -0.1700
Data Index: 5064890 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4405. Min Range: -7.4405
Max Act: 7.1280. Min Act: -0.1700
Data Index: 8299993 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4405. Min Range: -7.4405
Max Act: 7.1280. Min Act: -0.1700
Data Index: 795962 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4405. Min Range: -7.4405
Max Act: 7.0967. Min Act: -0.1700
Data Index: 6560072 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4405. Min Range: -7.4405
Max Act: 7.0342. Min Act: -0.1700
Data Index: 2924079 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4405. Min Range: -7.4405
Max Act: 7.0342. Min Act: -0.1700
Data Index: 1413092 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4405. Min Range: -7.4405
Max Act: 7.0030. Min Act: -0.1700
Data Index: 478938 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4405. Min Range: -7.4405
Max Act: 6.9717. Min Act: -0.1700
Data Index: 6252367 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4405. Min Range: -7.4405
Max Act: 6.9717. Min Act: -0.1700
Data Index: 7730685 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4405. Min Range: -7.4405
Max Act: 6.9405. Min Act: -0.1700
Data Index: 5167023 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4405. Min Range: -7.4405
Max Act: 6.9717. Min Act: -0.1700
Data Index: 1750907 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4405. Min Range: -7.4405
Max Act: 6.9405. Min Act: -0.1700
Data Index: 5279252 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19