Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9343. Min Range: -9.9343
Max Act: 9.9343. Min Act: -0.1700
Data Index: 1856478 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9343. Min Range: -9.9343
Max Act: 9.8093. Min Act: -0.1700
Data Index: 6516463 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9343. Min Range: -9.9343
Max Act: 9.6218. Min Act: -0.1700
Data Index: 3804427 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9343. Min Range: -9.9343
Max Act: 9.5593. Min Act: -0.1700
Data Index: 7884292 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9343. Min Range: -9.9343
Max Act: 9.5593. Min Act: -0.1700
Data Index: 3296952 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9343. Min Range: -9.9343
Max Act: 9.4968. Min Act: -0.1700
Data Index: 2490956 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9343. Min Range: -9.9343
Max Act: 9.4968. Min Act: -0.1700
Data Index: 1916965 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9343. Min Range: -9.9343
Max Act: 9.4968. Min Act: -0.1700
Data Index: 266772 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9343. Min Range: -9.9343
Max Act: 9.4343. Min Act: -0.1700
Data Index: 8267819 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9343. Min Range: -9.9343
Max Act: 9.4343. Min Act: -0.1700
Data Index: 5564191 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9343. Min Range: -9.9343
Max Act: 9.3718. Min Act: -0.1700
Data Index: 6016926 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9343. Min Range: -9.9343
Max Act: 9.3718. Min Act: -0.1700
Data Index: 5636127 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9343. Min Range: -9.9343
Max Act: 9.3093. Min Act: -0.1700
Data Index: 4423244 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9343. Min Range: -9.9343
Max Act: 9.3718. Min Act: -0.1700
Data Index: 5115375 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9343. Min Range: -9.9343
Max Act: 9.3718. Min Act: -0.1700
Data Index: 3807165 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9343. Min Range: -9.9343
Max Act: 9.3718. Min Act: -0.1700
Data Index: 8799949 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9343. Min Range: -9.9343
Max Act: 9.3093. Min Act: -0.1700
Data Index: 2267807 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9343. Min Range: -9.9343
Max Act: 9.3093. Min Act: -0.1700
Data Index: 8533624 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9343. Min Range: -9.9343
Max Act: 9.3093. Min Act: -0.1700
Data Index: 4326468 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9343. Min Range: -9.9343
Max Act: 9.3093. Min Act: -0.1700
Data Index: 3226029 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19