Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3373 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4322. Min Range: -5.4322
Max Act: 5.4322. Min Act: -0.1700
Data Index: 1229189 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4322. Min Range: -5.4322
Max Act: 5.3385. Min Act: -0.1700
Data Index: 329194 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4322. Min Range: -5.4322
Max Act: 5.2760. Min Act: -0.1700
Data Index: 2151001 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4322. Min Range: -5.4322
Max Act: 5.2135. Min Act: -0.1700
Data Index: 4022783 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4322. Min Range: -5.4322
Max Act: 5.1822. Min Act: -0.1700
Data Index: 1259475 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4322. Min Range: -5.4322
Max Act: 5.1510. Min Act: -0.1700
Data Index: 7167459 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4322. Min Range: -5.4322
Max Act: 5.1510. Min Act: -0.1700
Data Index: 3712245 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4322. Min Range: -5.4322
Max Act: 5.1822. Min Act: -0.1700
Data Index: 5667566 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4322. Min Range: -5.4322
Max Act: 5.1510. Min Act: -0.1700
Data Index: 1330072 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4322. Min Range: -5.4322
Max Act: 5.1510. Min Act: -0.1700
Data Index: 1625061 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4322. Min Range: -5.4322
Max Act: 5.1197. Min Act: -0.1700
Data Index: 4842676 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4322. Min Range: -5.4322
Max Act: 5.1197. Min Act: -0.1700
Data Index: 4164658 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4322. Min Range: -5.4322
Max Act: 5.1197. Min Act: -0.1700
Data Index: 5667561 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4322. Min Range: -5.4322
Max Act: 5.1197. Min Act: -0.1700
Data Index: 7944106 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4322. Min Range: -5.4322
Max Act: 5.1197. Min Act: -0.1700
Data Index: 2814172 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4322. Min Range: -5.4322
Max Act: 5.1197. Min Act: -0.1700
Data Index: 4089224 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4322. Min Range: -5.4322
Max Act: 5.0885. Min Act: -0.1700
Data Index: 3871699 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4322. Min Range: -5.4322
Max Act: 5.0885. Min Act: -0.1700
Data Index: 5667145 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4322. Min Range: -5.4322
Max Act: 5.0885. Min Act: -0.1700
Data Index: 2213969 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4322. Min Range: -5.4322
Max Act: 5.0885. Min Act: -0.1700
Data Index: 1322525 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19