Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2179 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6208. Min Range: -9.6208
Max Act: 9.6208. Min Act: -0.1700
Data Index: 4518145 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6208. Min Range: -9.6208
Max Act: 9.4958. Min Act: -0.1700
Data Index: 3086754 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6208. Min Range: -9.6208
Max Act: 9.4333. Min Act: -0.1700
Data Index: 1547323 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6208. Min Range: -9.6208
Max Act: 9.2458. Min Act: -0.1700
Data Index: 8072371 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6208. Min Range: -9.6208
Max Act: 9.1833. Min Act: -0.1700
Data Index: 6593601 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6208. Min Range: -9.6208
Max Act: 9.1833. Min Act: -0.1700
Data Index: 1433118 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6208. Min Range: -9.6208
Max Act: 9.1208. Min Act: -0.1700
Data Index: 3724822 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6208. Min Range: -9.6208
Max Act: 9.1208. Min Act: -0.1700
Data Index: 7616901 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6208. Min Range: -9.6208
Max Act: 9.0583. Min Act: -0.1700
Data Index: 306533 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6208. Min Range: -9.6208
Max Act: 8.9958. Min Act: -0.1700
Data Index: 5558304 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6208. Min Range: -9.6208
Max Act: 8.8708. Min Act: -0.1700
Data Index: 7269922 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6208. Min Range: -9.6208
Max Act: 8.8083. Min Act: -0.1700
Data Index: 8421201 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6208. Min Range: -9.6208
Max Act: 8.8083. Min Act: -0.1700
Data Index: 4109633 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6208. Min Range: -9.6208
Max Act: 8.8708. Min Act: -0.1700
Data Index: 4600518 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6208. Min Range: -9.6208
Max Act: 8.7458. Min Act: -0.1700
Data Index: 7369115 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6208. Min Range: -9.6208
Max Act: 8.7458. Min Act: -0.1700
Data Index: 6443782 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6208. Min Range: -9.6208
Max Act: 8.6833. Min Act: -0.1700
Data Index: 8735162 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6208. Min Range: -9.6208
Max Act: 8.7458. Min Act: -0.1700
Data Index: 7885511 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6208. Min Range: -9.6208
Max Act: 8.6833. Min Act: -0.1700
Data Index: 8462625 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6208. Min Range: -9.6208
Max Act: 8.6833. Min Act: -0.1700
Data Index: 2601754 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19