Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4157 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5241. Min Range: -4.5241
Max Act: 4.5241. Min Act: -0.1700
Data Index: 5788281 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5241. Min Range: -4.5241
Max Act: 4.4616. Min Act: -0.1700
Data Index: 604774 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5241. Min Range: -4.5241
Max Act: 4.4304. Min Act: -0.1700
Data Index: 3807393 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5241. Min Range: -4.5241
Max Act: 4.3991. Min Act: -0.1700
Data Index: 3572041 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5241. Min Range: -4.5241
Max Act: 4.3366. Min Act: -0.1700
Data Index: 5021832 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5241. Min Range: -4.5241
Max Act: 4.2741. Min Act: -0.1700
Data Index: 6850188 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5241. Min Range: -4.5241
Max Act: 4.2741. Min Act: -0.1700
Data Index: 7325589 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5241. Min Range: -4.5241
Max Act: 4.2741. Min Act: -0.1700
Data Index: 8344002 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5241. Min Range: -4.5241
Max Act: 4.2429. Min Act: -0.1700
Data Index: 3005062 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5241. Min Range: -4.5241
Max Act: 4.2429. Min Act: -0.1700
Data Index: 6574880 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5241. Min Range: -4.5241
Max Act: 4.2116. Min Act: -0.1700
Data Index: 3133251 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5241. Min Range: -4.5241
Max Act: 4.1804. Min Act: -0.1700
Data Index: 4370484 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5241. Min Range: -4.5241
Max Act: 4.1804. Min Act: -0.1700
Data Index: 901193 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5241. Min Range: -4.5241
Max Act: 4.2116. Min Act: -0.1700
Data Index: 2949803 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5241. Min Range: -4.5241
Max Act: 4.1804. Min Act: -0.1700
Data Index: 2167194 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5241. Min Range: -4.5241
Max Act: 4.1178. Min Act: -0.1700
Data Index: 1021882 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5241. Min Range: -4.5241
Max Act: 4.1178. Min Act: -0.1700
Data Index: 2683679 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5241. Min Range: -4.5241
Max Act: 4.1178. Min Act: -0.1700
Data Index: 1528551 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5241. Min Range: -4.5241
Max Act: 4.1491. Min Act: -0.1700
Data Index: 6889800 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5241. Min Range: -4.5241
Max Act: 4.1491. Min Act: -0.1700
Data Index: 8067585 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19