Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2846 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3999. Min Range: -6.3999
Max Act: 6.3999. Min Act: -0.1700
Data Index: 4300832 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3999. Min Range: -6.3999
Max Act: 6.0561. Min Act: -0.1700
Data Index: 7844076 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3999. Min Range: -6.3999
Max Act: 5.9311. Min Act: -0.1700
Data Index: 3933831 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3999. Min Range: -6.3999
Max Act: 5.9624. Min Act: -0.1700
Data Index: 6508899 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3999. Min Range: -6.3999
Max Act: 5.8999. Min Act: -0.1700
Data Index: 5282111 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3999. Min Range: -6.3999
Max Act: 5.8061. Min Act: -0.1700
Data Index: 3702500 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3999. Min Range: -6.3999
Max Act: 5.7436. Min Act: -0.1700
Data Index: 5706025 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3999. Min Range: -6.3999
Max Act: 5.7749. Min Act: -0.1700
Data Index: 3188332 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3999. Min Range: -6.3999
Max Act: 5.7749. Min Act: -0.1700
Data Index: 6466450 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3999. Min Range: -6.3999
Max Act: 5.7436. Min Act: -0.1700
Data Index: 2808755 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3999. Min Range: -6.3999
Max Act: 5.7436. Min Act: -0.1700
Data Index: 3403458 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3999. Min Range: -6.3999
Max Act: 5.7124. Min Act: -0.1700
Data Index: 5833255 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3999. Min Range: -6.3999
Max Act: 5.6811. Min Act: -0.1700
Data Index: 7625392 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3999. Min Range: -6.3999
Max Act: 5.6186. Min Act: -0.1700
Data Index: 5837327 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3999. Min Range: -6.3999
Max Act: 5.6811. Min Act: -0.1700
Data Index: 649748 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3999. Min Range: -6.3999
Max Act: 5.6186. Min Act: -0.1700
Data Index: 7621928 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3999. Min Range: -6.3999
Max Act: 5.5874. Min Act: -0.1700
Data Index: 7578879 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3999. Min Range: -6.3999
Max Act: 5.5561. Min Act: -0.1700
Data Index: 7399317 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3999. Min Range: -6.3999
Max Act: 5.5561. Min Act: -0.1700
Data Index: 3553841 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3999. Min Range: -6.3999
Max Act: 5.5874. Min Act: -0.1700
Data Index: 3199688 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19