Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2787 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8820. Min Range: -7.8820
Max Act: 7.8820. Min Act: -0.1700
Data Index: 8459788 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8820. Min Range: -7.8820
Max Act: 7.8195. Min Act: -0.1700
Data Index: 2547461 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8820. Min Range: -7.8820
Max Act: 7.6945. Min Act: -0.1700
Data Index: 3158504 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8820. Min Range: -7.8820
Max Act: 7.6945. Min Act: -0.1700
Data Index: 4470688 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8820. Min Range: -7.8820
Max Act: 7.5070. Min Act: -0.1700
Data Index: 8015102 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8820. Min Range: -7.8820
Max Act: 7.4758. Min Act: -0.1700
Data Index: 1280291 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8820. Min Range: -7.8820
Max Act: 7.4133. Min Act: -0.1700
Data Index: 5361346 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8820. Min Range: -7.8820
Max Act: 7.3820. Min Act: -0.1700
Data Index: 436093 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8820. Min Range: -7.8820
Max Act: 7.3508. Min Act: -0.1700
Data Index: 6379988 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8820. Min Range: -7.8820
Max Act: 7.3508. Min Act: -0.1700
Data Index: 8532973 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8820. Min Range: -7.8820
Max Act: 7.3508. Min Act: -0.1700
Data Index: 833857 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8820. Min Range: -7.8820
Max Act: 7.3195. Min Act: -0.1700
Data Index: 1025437 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8820. Min Range: -7.8820
Max Act: 7.3195. Min Act: -0.1700
Data Index: 6953890 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8820. Min Range: -7.8820
Max Act: 7.2883. Min Act: -0.1700
Data Index: 455184 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8820. Min Range: -7.8820
Max Act: 7.2883. Min Act: -0.1700
Data Index: 1815818 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8820. Min Range: -7.8820
Max Act: 7.2570. Min Act: -0.1700
Data Index: 40777 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8820. Min Range: -7.8820
Max Act: 7.2570. Min Act: -0.1700
Data Index: 6932067 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8820. Min Range: -7.8820
Max Act: 7.2570. Min Act: -0.1700
Data Index: 2958999 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8820. Min Range: -7.8820
Max Act: 7.2570. Min Act: -0.1700
Data Index: 6182700 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8820. Min Range: -7.8820
Max Act: 7.2570. Min Act: -0.1700
Data Index: 3520003 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19