Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2607 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3410. Min Range: -7.3410
Max Act: 7.3410. Min Act: -0.1700
Data Index: 721582 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3410. Min Range: -7.3410
Max Act: 7.2160. Min Act: -0.1700
Data Index: 5945080 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3410. Min Range: -7.3410
Max Act: 7.2472. Min Act: -0.1700
Data Index: 7148563 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3410. Min Range: -7.3410
Max Act: 7.2160. Min Act: -0.1700
Data Index: 7399031 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3410. Min Range: -7.3410
Max Act: 7.1535. Min Act: -0.1700
Data Index: 5471008 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3410. Min Range: -7.3410
Max Act: 7.1222. Min Act: -0.1700
Data Index: 5350702 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3410. Min Range: -7.3410
Max Act: 7.1222. Min Act: -0.1700
Data Index: 2071718 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3410. Min Range: -7.3410
Max Act: 7.0910. Min Act: -0.1700
Data Index: 8726835 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3410. Min Range: -7.3410
Max Act: 7.0285. Min Act: -0.1700
Data Index: 4881075 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3410. Min Range: -7.3410
Max Act: 7.0285. Min Act: -0.1700
Data Index: 2505732 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.9972. Min Act: -0.1700
Data Index: 4218182 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.9972. Min Act: -0.1700
Data Index: 5055097 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.9972. Min Act: -0.1700
Data Index: 462839 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.9660. Min Act: -0.1700
Data Index: 7366737 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.9660. Min Act: -0.1700
Data Index: 7801021 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.9660. Min Act: -0.1700
Data Index: 2751917 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.9347. Min Act: -0.1700
Data Index: 6144769 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.9347. Min Act: -0.1700
Data Index: 7484528 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.9347. Min Act: -0.1700
Data Index: 986213 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.9035. Min Act: -0.1700
Data Index: 2358014 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19