Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 593 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6003. Min Range: -3.6003
Max Act: 3.6003. Min Act: -0.1700
Data Index: 7032244 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6003. Min Range: -3.6003
Max Act: 3.5533. Min Act: -0.1700
Data Index: 1988 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6003. Min Range: -3.6003
Max Act: 3.5377. Min Act: -0.1700
Data Index: 7806735 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6003. Min Range: -3.6003
Max Act: 3.5377. Min Act: -0.1700
Data Index: 5588150 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6003. Min Range: -3.6003
Max Act: 3.5220. Min Act: -0.1700
Data Index: 562784 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6003. Min Range: -3.6003
Max Act: 3.5063. Min Act: -0.1700
Data Index: 1332671 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6003. Min Range: -3.6003
Max Act: 3.5220. Min Act: -0.1700
Data Index: 6123974 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6003. Min Range: -3.6003
Max Act: 3.4907. Min Act: -0.1700
Data Index: 7138764 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6003. Min Range: -3.6003
Max Act: 3.4750. Min Act: -0.1700
Data Index: 133745 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6003. Min Range: -3.6003
Max Act: 3.4907. Min Act: -0.1700
Data Index: 1494507 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6003. Min Range: -3.6003
Max Act: 3.4750. Min Act: -0.1700
Data Index: 7391286 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6003. Min Range: -3.6003
Max Act: 3.4750. Min Act: -0.1700
Data Index: 4411067 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6003. Min Range: -3.6003
Max Act: 3.4750. Min Act: -0.1700
Data Index: 628320 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6003. Min Range: -3.6003
Max Act: 3.4437. Min Act: -0.1700
Data Index: 5954972 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6003. Min Range: -3.6003
Max Act: 3.4437. Min Act: -0.1700
Data Index: 4718698 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6003. Min Range: -3.6003
Max Act: 3.4437. Min Act: -0.1700
Data Index: 7845880 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6003. Min Range: -3.6003
Max Act: 3.4437. Min Act: -0.1700
Data Index: 2932887 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6003. Min Range: -3.6003
Max Act: 3.4123. Min Act: -0.1700
Data Index: 1418673 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6003. Min Range: -3.6003
Max Act: 3.4123. Min Act: -0.1700
Data Index: 556012 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6003. Min Range: -3.6003
Max Act: 3.4123. Min Act: -0.1700
Data Index: 3133740 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19