Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 746 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8356. Min Range: -5.8356
Max Act: 5.8356. Min Act: -0.1700
Data Index: 790101 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8356. Min Range: -5.8356
Max Act: 5.6168. Min Act: -0.1700
Data Index: 1804410 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8356. Min Range: -5.8356
Max Act: 5.6168. Min Act: -0.1699
Data Index: 3987029 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8356. Min Range: -5.8356
Max Act: 5.5856. Min Act: -0.1700
Data Index: 4225240 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8356. Min Range: -5.8356
Max Act: 5.5856. Min Act: -0.1700
Data Index: 4049894 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8356. Min Range: -5.8356
Max Act: 5.5543. Min Act: -0.1700
Data Index: 743252 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8356. Min Range: -5.8356
Max Act: 5.4606. Min Act: -0.1700
Data Index: 4125538 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8356. Min Range: -5.8356
Max Act: 5.4918. Min Act: -0.1700
Data Index: 4525499 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8356. Min Range: -5.8356
Max Act: 5.4918. Min Act: -0.1700
Data Index: 7113899 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8356. Min Range: -5.8356
Max Act: 5.5231. Min Act: -0.1700
Data Index: 1359098 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8356. Min Range: -5.8356
Max Act: 5.4918. Min Act: -0.1700
Data Index: 7767683 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8356. Min Range: -5.8356
Max Act: 5.4606. Min Act: -0.1700
Data Index: 2469757 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8356. Min Range: -5.8356
Max Act: 5.4606. Min Act: -0.1700
Data Index: 4085889 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8356. Min Range: -5.8356
Max Act: 5.4293. Min Act: -0.1698
Data Index: 2671642 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8356. Min Range: -5.8356
Max Act: 5.4606. Min Act: -0.1700
Data Index: 7104293 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8356. Min Range: -5.8356
Max Act: 5.4293. Min Act: -0.1700
Data Index: 1968403 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8356. Min Range: -5.8356
Max Act: 5.4293. Min Act: -0.1700
Data Index: 3677147 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8356. Min Range: -5.8356
Max Act: 5.4293. Min Act: -0.1700
Data Index: 1811779 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8356. Min Range: -5.8356
Max Act: 5.4293. Min Act: -0.1700
Data Index: 4747731 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8356. Min Range: -5.8356
Max Act: 5.4606. Min Act: -0.1700
Data Index: 3636094 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19