Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3462 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7469. Min Range: -9.7469
Max Act: 9.7469. Min Act: -0.1700
Data Index: 4658534 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7469. Min Range: -9.7469
Max Act: 9.4969. Min Act: -0.1700
Data Index: 3425006 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7469. Min Range: -9.7469
Max Act: 9.4344. Min Act: -0.1700
Data Index: 209644 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7469. Min Range: -9.7469
Max Act: 9.4344. Min Act: -0.1700
Data Index: 8036385 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7469. Min Range: -9.7469
Max Act: 9.2469. Min Act: -0.1700
Data Index: 3962423 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7469. Min Range: -9.7469
Max Act: 9.0594. Min Act: -0.1700
Data Index: 4601061 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7469. Min Range: -9.7469
Max Act: 9.0594. Min Act: -0.1700
Data Index: 6918916 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7469. Min Range: -9.7469
Max Act: 8.9969. Min Act: -0.1700
Data Index: 2247445 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7469. Min Range: -9.7469
Max Act: 8.9344. Min Act: -0.1700
Data Index: 7845950 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7469. Min Range: -9.7469
Max Act: 8.9344. Min Act: -0.1700
Data Index: 7980658 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7469. Min Range: -9.7469
Max Act: 8.9969. Min Act: -0.1700
Data Index: 7505441 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7469. Min Range: -9.7469
Max Act: 8.8719. Min Act: -0.1700
Data Index: 3145289 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7469. Min Range: -9.7469
Max Act: 8.8719. Min Act: -0.1700
Data Index: 4915174 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7469. Min Range: -9.7469
Max Act: 8.8094. Min Act: -0.1700
Data Index: 3595962 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7469. Min Range: -9.7469
Max Act: 8.8094. Min Act: -0.1700
Data Index: 5768290 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7469. Min Range: -9.7469
Max Act: 8.8094. Min Act: -0.1700
Data Index: 8468779 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7469. Min Range: -9.7469
Max Act: 8.8094. Min Act: -0.1700
Data Index: 1785151 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7469. Min Range: -9.7469
Max Act: 8.8094. Min Act: -0.1700
Data Index: 5817831 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7469. Min Range: -9.7469
Max Act: 8.7469. Min Act: -0.1700
Data Index: 7796281 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7469. Min Range: -9.7469
Max Act: 8.7469. Min Act: -0.1700
Data Index: 6856931 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19