Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 714 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5899. Min Range: -9.5899
Max Act: 9.5899. Min Act: -0.1700
Data Index: 5747242 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5899. Min Range: -9.5899
Max Act: 9.1524. Min Act: -0.1700
Data Index: 3780234 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5899. Min Range: -9.5899
Max Act: 9.0899. Min Act: -0.1700
Data Index: 5003577 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5899. Min Range: -9.5899
Max Act: 9.0274. Min Act: -0.1700
Data Index: 8446591 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5899. Min Range: -9.5899
Max Act: 8.8399. Min Act: -0.1700
Data Index: 7481073 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5899. Min Range: -9.5899
Max Act: 8.8399. Min Act: -0.1700
Data Index: 5067378 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5899. Min Range: -9.5899
Max Act: 8.8399. Min Act: -0.1700
Data Index: 3866085 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5899. Min Range: -9.5899
Max Act: 8.8399. Min Act: -0.1700
Data Index: 3866094 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5899. Min Range: -9.5899
Max Act: 8.8399. Min Act: -0.1700
Data Index: 521926 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5899. Min Range: -9.5899
Max Act: 8.7774. Min Act: -0.1700
Data Index: 6278752 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5899. Min Range: -9.5899
Max Act: 8.7774. Min Act: -0.1700
Data Index: 567872 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5899. Min Range: -9.5899
Max Act: 8.7774. Min Act: -0.1700
Data Index: 7774354 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5899. Min Range: -9.5899
Max Act: 8.7774. Min Act: -0.1700
Data Index: 6957153 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5899. Min Range: -9.5899
Max Act: 8.7774. Min Act: -0.1700
Data Index: 772471 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5899. Min Range: -9.5899
Max Act: 8.7774. Min Act: -0.1700
Data Index: 5190595 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5899. Min Range: -9.5899
Max Act: 8.7149. Min Act: -0.1700
Data Index: 5471470 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5899. Min Range: -9.5899
Max Act: 8.7149. Min Act: -0.1700
Data Index: 4855053 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5899. Min Range: -9.5899
Max Act: 8.6524. Min Act: -0.1700
Data Index: 2082360 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5899. Min Range: -9.5899
Max Act: 8.5899. Min Act: -0.1700
Data Index: 3452667 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5899. Min Range: -9.5899
Max Act: 8.6524. Min Act: -0.1700
Data Index: 3733019 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19