Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2080 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7994. Min Range: -6.7994
Max Act: 6.7994. Min Act: -0.1700
Data Index: 4137680 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7994. Min Range: -6.7994
Max Act: 6.6119. Min Act: -0.1700
Data Index: 3606397 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7994. Min Range: -6.7994
Max Act: 6.4869. Min Act: -0.1700
Data Index: 2490701 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7994. Min Range: -6.7994
Max Act: 6.4557. Min Act: -0.1700
Data Index: 8202075 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7994. Min Range: -6.7994
Max Act: 6.3307. Min Act: -0.1700
Data Index: 5311066 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7994. Min Range: -6.7994
Max Act: 6.2994. Min Act: -0.1700
Data Index: 5885789 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7994. Min Range: -6.7994
Max Act: 6.3307. Min Act: -0.1700
Data Index: 3056461 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7994. Min Range: -6.7994
Max Act: 6.3307. Min Act: -0.1700
Data Index: 7624884 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7994. Min Range: -6.7994
Max Act: 6.3307. Min Act: -0.1700
Data Index: 6568600 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7994. Min Range: -6.7994
Max Act: 6.2369. Min Act: -0.1700
Data Index: 2354925 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7994. Min Range: -6.7994
Max Act: 6.2369. Min Act: -0.1700
Data Index: 1378916 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7994. Min Range: -6.7994
Max Act: 6.2057. Min Act: -0.1700
Data Index: 1945089 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7994. Min Range: -6.7994
Max Act: 6.2057. Min Act: -0.1700
Data Index: 7471725 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7994. Min Range: -6.7994
Max Act: 6.2057. Min Act: -0.1700
Data Index: 2740721 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7994. Min Range: -6.7994
Max Act: 6.2057. Min Act: -0.1700
Data Index: 8094655 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7994. Min Range: -6.7994
Max Act: 6.2057. Min Act: -0.1700
Data Index: 1612210 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7994. Min Range: -6.7994
Max Act: 6.1744. Min Act: -0.1700
Data Index: 4351561 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7994. Min Range: -6.7994
Max Act: 6.1432. Min Act: -0.1700
Data Index: 1413586 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7994. Min Range: -6.7994
Max Act: 6.1432. Min Act: -0.1700
Data Index: 6166873 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7994. Min Range: -6.7994
Max Act: 6.1432. Min Act: -0.1700
Data Index: 4865611 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19