Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1592 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3595. Min Range: -4.3595
Max Act: 4.3595. Min Act: -0.1700
Data Index: 8528515 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3595. Min Range: -4.3595
Max Act: 4.2970. Min Act: -0.1700
Data Index: 327838 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3595. Min Range: -4.3595
Max Act: 4.2658. Min Act: -0.1700
Data Index: 4913057 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3595. Min Range: -4.3595
Max Act: 4.2033. Min Act: -0.1700
Data Index: 7845758 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3595. Min Range: -4.3595
Max Act: 4.2033. Min Act: -0.1700
Data Index: 3233265 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3595. Min Range: -4.3595
Max Act: 4.1720. Min Act: -0.1700
Data Index: 6473454 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3595. Min Range: -4.3595
Max Act: 4.1720. Min Act: -0.1700
Data Index: 4150056 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3595. Min Range: -4.3595
Max Act: 4.1408. Min Act: -0.1700
Data Index: 3738178 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3595. Min Range: -4.3595
Max Act: 4.1408. Min Act: -0.1700
Data Index: 5335709 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3595. Min Range: -4.3595
Max Act: 4.1095. Min Act: -0.1700
Data Index: 2532345 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3595. Min Range: -4.3595
Max Act: 4.1095. Min Act: -0.1700
Data Index: 916600 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3595. Min Range: -4.3595
Max Act: 4.1095. Min Act: -0.1700
Data Index: 3556490 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3595. Min Range: -4.3595
Max Act: 4.0783. Min Act: -0.1700
Data Index: 1990768 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3595. Min Range: -4.3595
Max Act: 4.0470. Min Act: -0.1700
Data Index: 6378825 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3595. Min Range: -4.3595
Max Act: 4.0470. Min Act: -0.1700
Data Index: 6383189 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3595. Min Range: -4.3595
Max Act: 4.0470. Min Act: -0.1700
Data Index: 5769226 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3595. Min Range: -4.3595
Max Act: 4.0470. Min Act: -0.1700
Data Index: 747948 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3595. Min Range: -4.3595
Max Act: 4.0470. Min Act: -0.1700
Data Index: 4679252 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3595. Min Range: -4.3595
Max Act: 4.0157. Min Act: -0.1700
Data Index: 3694579 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3595. Min Range: -4.3595
Max Act: 4.0157. Min Act: -0.1700
Data Index: 8367400 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19