Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5828 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6884. Min Range: -7.6884
Max Act: 7.6884. Min Act: -0.1700
Data Index: 1412606 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6884. Min Range: -7.6884
Max Act: 7.6571. Min Act: -0.1700
Data Index: 1678551 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6884. Min Range: -7.6884
Max Act: 7.6259. Min Act: -0.1700
Data Index: 484174 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6884. Min Range: -7.6884
Max Act: 7.5946. Min Act: -0.1700
Data Index: 8001542 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6884. Min Range: -7.6884
Max Act: 7.5946. Min Act: -0.1700
Data Index: 169886 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6884. Min Range: -7.6884
Max Act: 7.5946. Min Act: -0.1700
Data Index: 1027856 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6884. Min Range: -7.6884
Max Act: 7.4384. Min Act: -0.1700
Data Index: 8194781 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6884. Min Range: -7.6884
Max Act: 7.4384. Min Act: -0.1700
Data Index: 8690857 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6884. Min Range: -7.6884
Max Act: 7.3759. Min Act: -0.1700
Data Index: 4213535 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6884. Min Range: -7.6884
Max Act: 7.4071. Min Act: -0.1700
Data Index: 6318938 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6884. Min Range: -7.6884
Max Act: 7.3446. Min Act: -0.1700
Data Index: 2187826 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6884. Min Range: -7.6884
Max Act: 7.3446. Min Act: -0.1700
Data Index: 4363648 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6884. Min Range: -7.6884
Max Act: 7.3759. Min Act: -0.1700
Data Index: 6115335 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6884. Min Range: -7.6884
Max Act: 7.3134. Min Act: -0.1700
Data Index: 4858254 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6884. Min Range: -7.6884
Max Act: 7.3134. Min Act: -0.1700
Data Index: 3908713 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6884. Min Range: -7.6884
Max Act: 7.2821. Min Act: -0.1700
Data Index: 343082 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6884. Min Range: -7.6884
Max Act: 7.2821. Min Act: -0.1700
Data Index: 8169186 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6884. Min Range: -7.6884
Max Act: 7.2821. Min Act: -0.1700
Data Index: 3710606 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6884. Min Range: -7.6884
Max Act: 7.2821. Min Act: -0.1700
Data Index: 1014029 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6884. Min Range: -7.6884
Max Act: 7.2509. Min Act: -0.1700
Data Index: 4234155 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19