Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3539 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8353. Min Range: -3.8353
Max Act: 3.8353. Min Act: -0.1700
Data Index: 4274742 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8353. Min Range: -3.8353
Max Act: 3.6945. Min Act: -0.1700
Data Index: 6347623 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8353. Min Range: -3.8353
Max Act: 3.5537. Min Act: -0.1700
Data Index: 1820885 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8353. Min Range: -3.8353
Max Act: 3.4441. Min Act: -0.1700
Data Index: 5141178 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8353. Min Range: -3.8353
Max Act: 3.4284. Min Act: -0.1700
Data Index: 1731976 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8353. Min Range: -3.8353
Max Act: 3.4127. Min Act: -0.1700
Data Index: 3533138 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8353. Min Range: -3.8353
Max Act: 3.3970. Min Act: -0.1700
Data Index: 4141461 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8353. Min Range: -3.8353
Max Act: 3.3970. Min Act: -0.1700
Data Index: 6113842 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8353. Min Range: -3.8353
Max Act: 3.3657. Min Act: -0.1700
Data Index: 8612516 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8353. Min Range: -3.8353
Max Act: 3.3657. Min Act: -0.1700
Data Index: 1259355 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8353. Min Range: -3.8353
Max Act: 3.3343. Min Act: -0.1700
Data Index: 3109413 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8353. Min Range: -3.8353
Max Act: 3.3500. Min Act: -0.1700
Data Index: 1871275 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8353. Min Range: -3.8353
Max Act: 3.3343. Min Act: -0.1700
Data Index: 7456368 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8353. Min Range: -3.8353
Max Act: 3.3186. Min Act: -0.1700
Data Index: 3085967 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8353. Min Range: -3.8353
Max Act: 3.3186. Min Act: -0.1700
Data Index: 7375889 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8353. Min Range: -3.8353
Max Act: 3.3029. Min Act: -0.1700
Data Index: 8408162 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8353. Min Range: -3.8353
Max Act: 3.2872. Min Act: -0.1700
Data Index: 2587463 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8353. Min Range: -3.8353
Max Act: 3.3029. Min Act: -0.1700
Data Index: 320174 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8353. Min Range: -3.8353
Max Act: 3.2872. Min Act: -0.1700
Data Index: 7908069 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8353. Min Range: -3.8353
Max Act: 3.2872. Min Act: -0.1700
Data Index: 2233225 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19