Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1581 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7882. Min Range: -7.7882
Max Act: 7.7882. Min Act: -0.1700
Data Index: 6723001 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7882. Min Range: -7.7882
Max Act: 7.5070. Min Act: -0.1700
Data Index: 7580471 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7882. Min Range: -7.7882
Max Act: 7.2882. Min Act: -0.1700
Data Index: 465438 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7882. Min Range: -7.7882
Max Act: 7.1007. Min Act: -0.1700
Data Index: 3952384 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7882. Min Range: -7.7882
Max Act: 7.0070. Min Act: -0.1700
Data Index: 7519829 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7882. Min Range: -7.7882
Max Act: 6.9445. Min Act: -0.1700
Data Index: 6712363 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7882. Min Range: -7.7882
Max Act: 6.9445. Min Act: -0.1700
Data Index: 2145554 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7882. Min Range: -7.7882
Max Act: 6.9132. Min Act: -0.1700
Data Index: 6171686 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7882. Min Range: -7.7882
Max Act: 6.8195. Min Act: -0.1700
Data Index: 8021277 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7882. Min Range: -7.7882
Max Act: 6.8195. Min Act: -0.1700
Data Index: 8409871 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7882. Min Range: -7.7882
Max Act: 6.8195. Min Act: -0.1700
Data Index: 6810391 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7882. Min Range: -7.7882
Max Act: 6.8195. Min Act: -0.1700
Data Index: 4847072 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7882. Min Range: -7.7882
Max Act: 6.8195. Min Act: -0.1700
Data Index: 4691008 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7882. Min Range: -7.7882
Max Act: 6.7570. Min Act: -0.1700
Data Index: 4853283 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7882. Min Range: -7.7882
Max Act: 6.7257. Min Act: -0.1700
Data Index: 1095082 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7882. Min Range: -7.7882
Max Act: 6.7257. Min Act: -0.1700
Data Index: 4852082 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7882. Min Range: -7.7882
Max Act: 6.7570. Min Act: -0.1700
Data Index: 510847 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7882. Min Range: -7.7882
Max Act: 6.7257. Min Act: -0.1700
Data Index: 8665866 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7882. Min Range: -7.7882
Max Act: 6.6632. Min Act: -0.1700
Data Index: 6158245 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7882. Min Range: -7.7882
Max Act: 6.6632. Min Act: -0.1700
Data Index: 395303 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19