Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3871 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4144. Min Range: -7.4144
Max Act: 7.4144. Min Act: -0.1700
Data Index: 2430919 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4144. Min Range: -7.4144
Max Act: 7.3519. Min Act: -0.1700
Data Index: 4705155 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4144. Min Range: -7.4144
Max Act: 7.2581. Min Act: -0.1700
Data Index: 7011653 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4144. Min Range: -7.4144
Max Act: 7.1331. Min Act: -0.1700
Data Index: 5268350 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4144. Min Range: -7.4144
Max Act: 7.0706. Min Act: -0.1700
Data Index: 1413396 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4144. Min Range: -7.4144
Max Act: 7.0394. Min Act: -0.1700
Data Index: 1645593 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4144. Min Range: -7.4144
Max Act: 7.0081. Min Act: -0.1700
Data Index: 6768077 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4144. Min Range: -7.4144
Max Act: 6.9456. Min Act: -0.1700
Data Index: 7184912 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4144. Min Range: -7.4144
Max Act: 6.9456. Min Act: -0.1700
Data Index: 6444645 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4144. Min Range: -7.4144
Max Act: 6.9144. Min Act: -0.1700
Data Index: 2938471 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4144. Min Range: -7.4144
Max Act: 6.8831. Min Act: -0.1700
Data Index: 7822389 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4144. Min Range: -7.4144
Max Act: 6.8831. Min Act: -0.1700
Data Index: 6196161 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4144. Min Range: -7.4144
Max Act: 6.8519. Min Act: -0.1700
Data Index: 4518586 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4144. Min Range: -7.4144
Max Act: 6.8206. Min Act: -0.1700
Data Index: 4052902 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4144. Min Range: -7.4144
Max Act: 6.7894. Min Act: -0.1700
Data Index: 4452760 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4144. Min Range: -7.4144
Max Act: 6.7894. Min Act: -0.1700
Data Index: 8748153 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4144. Min Range: -7.4144
Max Act: 6.7894. Min Act: -0.1700
Data Index: 3781944 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4144. Min Range: -7.4144
Max Act: 6.7894. Min Act: -0.1700
Data Index: 1650211 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4144. Min Range: -7.4144
Max Act: 6.7581. Min Act: -0.1700
Data Index: 2070228 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4144. Min Range: -7.4144
Max Act: 6.6956. Min Act: -0.1700
Data Index: 2191500 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19