Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3619 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8691. Min Range: -8.8691
Max Act: 8.8691. Min Act: -0.1700
Data Index: 4242785 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8691. Min Range: -8.8691
Max Act: 8.7441. Min Act: -0.1700
Data Index: 2429175 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8691. Min Range: -8.8691
Max Act: 8.6816. Min Act: -0.1700
Data Index: 2098174 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8691. Min Range: -8.8691
Max Act: 8.6191. Min Act: -0.1700
Data Index: 6005170 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8691. Min Range: -8.8691
Max Act: 8.4941. Min Act: -0.1700
Data Index: 4085043 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8691. Min Range: -8.8691
Max Act: 8.5566. Min Act: -0.1700
Data Index: 7462904 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8691. Min Range: -8.8691
Max Act: 8.4316. Min Act: -0.1700
Data Index: 4333320 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8691. Min Range: -8.8691
Max Act: 8.4316. Min Act: -0.1700
Data Index: 7649355 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8691. Min Range: -8.8691
Max Act: 8.4316. Min Act: -0.1700
Data Index: 3111253 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8691. Min Range: -8.8691
Max Act: 8.4316. Min Act: -0.1700
Data Index: 7481403 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8691. Min Range: -8.8691
Max Act: 8.3066. Min Act: -0.1700
Data Index: 6131173 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8691. Min Range: -8.8691
Max Act: 8.3691. Min Act: -0.1700
Data Index: 792983 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8691. Min Range: -8.8691
Max Act: 8.3691. Min Act: -0.1700
Data Index: 8185007 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8691. Min Range: -8.8691
Max Act: 8.3066. Min Act: -0.1700
Data Index: 4264355 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8691. Min Range: -8.8691
Max Act: 8.3066. Min Act: -0.1700
Data Index: 1386599 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8691. Min Range: -8.8691
Max Act: 8.2441. Min Act: -0.1700
Data Index: 5970783 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8691. Min Range: -8.8691
Max Act: 8.3066. Min Act: -0.1700
Data Index: 1355152 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8691. Min Range: -8.8691
Max Act: 8.3066. Min Act: -0.1700
Data Index: 792984 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8691. Min Range: -8.8691
Max Act: 8.2441. Min Act: -0.1700
Data Index: 1497444 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8691. Min Range: -8.8691
Max Act: 8.2441. Min Act: -0.1700
Data Index: 496822 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19