Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3744 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4510. Min Range: -6.4510
Max Act: 6.4510. Min Act: -0.1700
Data Index: 4169609 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4510. Min Range: -6.4510
Max Act: 6.4198. Min Act: -0.1700
Data Index: 7636076 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4510. Min Range: -6.4510
Max Act: 6.4198. Min Act: -0.1700
Data Index: 2062888 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4510. Min Range: -6.4510
Max Act: 6.3260. Min Act: -0.1700
Data Index: 1511166 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4510. Min Range: -6.4510
Max Act: 6.3260. Min Act: -0.1700
Data Index: 4958633 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4510. Min Range: -6.4510
Max Act: 6.2635. Min Act: -0.1700
Data Index: 6058881 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4510. Min Range: -6.4510
Max Act: 6.2323. Min Act: -0.1700
Data Index: 6382781 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4510. Min Range: -6.4510
Max Act: 6.2010. Min Act: -0.1700
Data Index: 6812161 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4510. Min Range: -6.4510
Max Act: 6.1698. Min Act: -0.1700
Data Index: 1182388 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4510. Min Range: -6.4510
Max Act: 6.1698. Min Act: -0.1700
Data Index: 360523 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4510. Min Range: -6.4510
Max Act: 6.1385. Min Act: -0.1700
Data Index: 4403028 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4510. Min Range: -6.4510
Max Act: 6.1385. Min Act: -0.1700
Data Index: 678029 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4510. Min Range: -6.4510
Max Act: 6.1385. Min Act: -0.1700
Data Index: 5934645 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4510. Min Range: -6.4510
Max Act: 6.1073. Min Act: -0.1700
Data Index: 6382774 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4510. Min Range: -6.4510
Max Act: 6.0448. Min Act: -0.1700
Data Index: 910260 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4510. Min Range: -6.4510
Max Act: 6.0135. Min Act: -0.1700
Data Index: 5385988 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4510. Min Range: -6.4510
Max Act: 6.0135. Min Act: -0.1700
Data Index: 7635155 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4510. Min Range: -6.4510
Max Act: 6.0135. Min Act: -0.1700
Data Index: 2797248 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4510. Min Range: -6.4510
Max Act: 6.0135. Min Act: -0.1700
Data Index: 2557594 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4510. Min Range: -6.4510
Max Act: 5.9823. Min Act: -0.1700
Data Index: 5371650 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19