Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 112 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1526. Min Range: -3.1526
Max Act: 3.1526. Min Act: -0.1700
Data Index: 6157173 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1526. Min Range: -3.1526
Max Act: 3.1526. Min Act: -0.1700
Data Index: 8254696 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1526. Min Range: -3.1526
Max Act: 3.1054. Min Act: -0.1700
Data Index: 505029 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1526. Min Range: -3.1526
Max Act: 3.1054. Min Act: -0.1700
Data Index: 6346831 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1526. Min Range: -3.1526
Max Act: 3.1211. Min Act: -0.1700
Data Index: 1822518 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1526. Min Range: -3.1526
Max Act: 3.1211. Min Act: -0.1700
Data Index: 4958983 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1526. Min Range: -3.1526
Max Act: 3.0739. Min Act: -0.1700
Data Index: 8340467 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1526. Min Range: -3.1526
Max Act: 3.0423. Min Act: -0.1700
Data Index: 1133473 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1526. Min Range: -3.1526
Max Act: 3.0423. Min Act: -0.1700
Data Index: 5637995 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1526. Min Range: -3.1526
Max Act: 3.0423. Min Act: -0.1700
Data Index: 2008957 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1526. Min Range: -3.1526
Max Act: 3.0423. Min Act: -0.1700
Data Index: 4011942 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1526. Min Range: -3.1526
Max Act: 3.0423. Min Act: -0.1700
Data Index: 3216019 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1526. Min Range: -3.1526
Max Act: 3.0107. Min Act: -0.1700
Data Index: 994341 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1526. Min Range: -3.1526
Max Act: 3.0107. Min Act: -0.1700
Data Index: 2141795 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1526. Min Range: -3.1526
Max Act: 3.0107. Min Act: -0.1700
Data Index: 6285438 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1526. Min Range: -3.1526
Max Act: 3.0107. Min Act: -0.1700
Data Index: 2767061 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1526. Min Range: -3.1526
Max Act: 3.0107. Min Act: -0.1700
Data Index: 7553838 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1526. Min Range: -3.1526
Max Act: 3.0107. Min Act: -0.1700
Data Index: 5365943 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1526. Min Range: -3.1526
Max Act: 3.0107. Min Act: -0.1700
Data Index: 3841763 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1526. Min Range: -3.1526
Max Act: 2.9949. Min Act: -0.1700
Data Index: 3600832 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19