Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4980 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4356. Min Range: -9.4356
Max Act: 9.4356. Min Act: -0.1700
Data Index: 5565283 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4356. Min Range: -9.4356
Max Act: 8.9981. Min Act: -0.1700
Data Index: 6133660 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4356. Min Range: -9.4356
Max Act: 8.8731. Min Act: -0.1700
Data Index: 7806918 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4356. Min Range: -9.4356
Max Act: 8.6231. Min Act: -0.1700
Data Index: 1356433 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4356. Min Range: -9.4356
Max Act: 8.5606. Min Act: -0.1700
Data Index: 7969425 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4356. Min Range: -9.4356
Max Act: 8.4981. Min Act: -0.1700
Data Index: 429195 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4356. Min Range: -9.4356
Max Act: 8.4981. Min Act: -0.1700
Data Index: 1458277 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4356. Min Range: -9.4356
Max Act: 8.4981. Min Act: -0.1700
Data Index: 3475295 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4356. Min Range: -9.4356
Max Act: 8.4981. Min Act: -0.1700
Data Index: 4141261 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4356. Min Range: -9.4356
Max Act: 8.4981. Min Act: -0.1700
Data Index: 1824295 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4356. Min Range: -9.4356
Max Act: 8.4356. Min Act: -0.1700
Data Index: 5293728 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4356. Min Range: -9.4356
Max Act: 8.3731. Min Act: -0.1700
Data Index: 93963 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4356. Min Range: -9.4356
Max Act: 8.4356. Min Act: -0.1700
Data Index: 7702471 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4356. Min Range: -9.4356
Max Act: 8.4356. Min Act: -0.1700
Data Index: 2663032 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4356. Min Range: -9.4356
Max Act: 8.3731. Min Act: -0.1700
Data Index: 3570350 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4356. Min Range: -9.4356
Max Act: 8.3731. Min Act: -0.1700
Data Index: 3740316 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4356. Min Range: -9.4356
Max Act: 8.3106. Min Act: -0.1700
Data Index: 7369209 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4356. Min Range: -9.4356
Max Act: 8.3731. Min Act: -0.1700
Data Index: 3010755 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4356. Min Range: -9.4356
Max Act: 8.3731. Min Act: -0.1700
Data Index: 8396455 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4356. Min Range: -9.4356
Max Act: 8.3731. Min Act: -0.1698
Data Index: 5458044 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19