Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4315 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.9827. Min Act: -0.1700
Data Index: 2448075 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.7952. Min Act: -0.1700
Data Index: 8448978 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.7952. Min Act: -0.1700
Data Index: 5055189 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.7640. Min Act: -0.1700
Data Index: 8816334 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.7327. Min Act: -0.1700
Data Index: 2932898 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.5452. Min Act: -0.1700
Data Index: 4088069 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.4202. Min Act: -0.1700
Data Index: 3528702 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.4202. Min Act: -0.1700
Data Index: 64825 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.4202. Min Act: -0.1700
Data Index: 2288362 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.4202. Min Act: -0.1700
Data Index: 3509103 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.3890. Min Act: -0.1700
Data Index: 5870864 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.3890. Min Act: -0.1700
Data Index: 2051546 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.3890. Min Act: -0.1700
Data Index: 1984424 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.3890. Min Act: -0.1700
Data Index: 5031010 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.3577. Min Act: -0.1700
Data Index: 2794923 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.3265. Min Act: -0.1700
Data Index: 7237024 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.3890. Min Act: -0.1700
Data Index: 8420473 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.3265. Min Act: -0.1700
Data Index: 6887352 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.3265. Min Act: -0.1700
Data Index: 6990569 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.2952. Min Act: -0.1700
Data Index: 8375937 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19