Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2359 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2426. Min Range: -7.2426
Max Act: 7.2426. Min Act: -0.1700
Data Index: 2298603 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2426. Min Range: -7.2426
Max Act: 7.2426. Min Act: -0.1700
Data Index: 136691 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2426. Min Range: -7.2426
Max Act: 7.0864. Min Act: -0.1700
Data Index: 8578085 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2426. Min Range: -7.2426
Max Act: 7.1176. Min Act: -0.1700
Data Index: 202836 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2426. Min Range: -7.2426
Max Act: 7.1176. Min Act: -0.1700
Data Index: 2170482 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2426. Min Range: -7.2426
Max Act: 7.0551. Min Act: -0.1700
Data Index: 7353574 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2426. Min Range: -7.2426
Max Act: 6.9926. Min Act: -0.1700
Data Index: 7435166 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2426. Min Range: -7.2426
Max Act: 6.9301. Min Act: -0.1700
Data Index: 3740395 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2426. Min Range: -7.2426
Max Act: 6.9614. Min Act: -0.1700
Data Index: 8541987 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2426. Min Range: -7.2426
Max Act: 6.8989. Min Act: -0.1700
Data Index: 1254588 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2426. Min Range: -7.2426
Max Act: 6.8989. Min Act: -0.1700
Data Index: 4505939 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2426. Min Range: -7.2426
Max Act: 6.8676. Min Act: -0.1700
Data Index: 4784041 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2426. Min Range: -7.2426
Max Act: 6.8364. Min Act: -0.1700
Data Index: 963099 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2426. Min Range: -7.2426
Max Act: 6.8051. Min Act: -0.1700
Data Index: 651414 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2426. Min Range: -7.2426
Max Act: 6.8051. Min Act: -0.1700
Data Index: 5674613 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2426. Min Range: -7.2426
Max Act: 6.8051. Min Act: -0.1700
Data Index: 2157125 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2426. Min Range: -7.2426
Max Act: 6.7739. Min Act: -0.1700
Data Index: 8759293 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2426. Min Range: -7.2426
Max Act: 6.7739. Min Act: -0.1700
Data Index: 4197001 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2426. Min Range: -7.2426
Max Act: 6.7426. Min Act: -0.1700
Data Index: 6996680 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2426. Min Range: -7.2426
Max Act: 6.7114. Min Act: -0.1700
Data Index: 4939295 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19