Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2811 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1344. Min Range: -5.1344
Max Act: 5.1344. Min Act: -0.1700
Data Index: 7936872 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1344. Min Range: -5.1344
Max Act: 5.0407. Min Act: -0.1700
Data Index: 7441953 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1344. Min Range: -5.1344
Max Act: 5.0407. Min Act: -0.1700
Data Index: 1930704 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1344. Min Range: -5.1344
Max Act: 5.0094. Min Act: -0.1700
Data Index: 4882378 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1344. Min Range: -5.1344
Max Act: 5.0094. Min Act: -0.1700
Data Index: 3484456 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1344. Min Range: -5.1344
Max Act: 5.0094. Min Act: -0.1700
Data Index: 3051932 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1344. Min Range: -5.1344
Max Act: 4.9782. Min Act: -0.1700
Data Index: 6021460 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1344. Min Range: -5.1344
Max Act: 4.9782. Min Act: -0.1700
Data Index: 8493247 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1344. Min Range: -5.1344
Max Act: 4.9782. Min Act: -0.1700
Data Index: 3444414 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1344. Min Range: -5.1344
Max Act: 4.9782. Min Act: -0.1700
Data Index: 6821260 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1344. Min Range: -5.1344
Max Act: 4.9782. Min Act: -0.1700
Data Index: 2515574 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1344. Min Range: -5.1344
Max Act: 4.9782. Min Act: -0.1700
Data Index: 2506093 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1344. Min Range: -5.1344
Max Act: 4.9782. Min Act: -0.1700
Data Index: 3062275 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1344. Min Range: -5.1344
Max Act: 4.9469. Min Act: -0.1700
Data Index: 2102321 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1344. Min Range: -5.1344
Max Act: 4.9469. Min Act: -0.1700
Data Index: 1678713 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1344. Min Range: -5.1344
Max Act: 4.9469. Min Act: -0.1700
Data Index: 6868507 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1344. Min Range: -5.1344
Max Act: 4.9157. Min Act: -0.1700
Data Index: 2928536 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1344. Min Range: -5.1344
Max Act: 4.9469. Min Act: -0.1700
Data Index: 5320852 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1344. Min Range: -5.1344
Max Act: 4.9469. Min Act: -0.1700
Data Index: 4359664 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1344. Min Range: -5.1344
Max Act: 4.9157. Min Act: -0.1700
Data Index: 3492525 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19