Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1692 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8235. Min Range: -5.8235
Max Act: 5.8235. Min Act: -0.1700
Data Index: 19654 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8235. Min Range: -5.8235
Max Act: 5.8235. Min Act: -0.1700
Data Index: 3993323 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8235. Min Range: -5.8235
Max Act: 5.7923. Min Act: -0.1700
Data Index: 1006788 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8235. Min Range: -5.8235
Max Act: 5.7610. Min Act: -0.1700
Data Index: 972317 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8235. Min Range: -5.8235
Max Act: 5.7610. Min Act: -0.1700
Data Index: 1270296 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8235. Min Range: -5.8235
Max Act: 5.7298. Min Act: -0.1700
Data Index: 6933928 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8235. Min Range: -5.8235
Max Act: 5.6673. Min Act: -0.1700
Data Index: 2414342 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8235. Min Range: -5.8235
Max Act: 5.6673. Min Act: -0.1700
Data Index: 4214756 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8235. Min Range: -5.8235
Max Act: 5.6360. Min Act: -0.1700
Data Index: 7566089 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8235. Min Range: -5.8235
Max Act: 5.6360. Min Act: -0.1700
Data Index: 380650 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8235. Min Range: -5.8235
Max Act: 5.5735. Min Act: -0.1700
Data Index: 6812325 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8235. Min Range: -5.8235
Max Act: 5.6048. Min Act: -0.1700
Data Index: 6381520 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8235. Min Range: -5.8235
Max Act: 5.5735. Min Act: -0.1700
Data Index: 3216656 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8235. Min Range: -5.8235
Max Act: 5.6048. Min Act: -0.1700
Data Index: 3658599 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8235. Min Range: -5.8235
Max Act: 5.5735. Min Act: -0.1700
Data Index: 1030755 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8235. Min Range: -5.8235
Max Act: 5.5735. Min Act: -0.1700
Data Index: 3077891 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8235. Min Range: -5.8235
Max Act: 5.5423. Min Act: -0.1700
Data Index: 2632122 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8235. Min Range: -5.8235
Max Act: 5.5423. Min Act: -0.1700
Data Index: 6994595 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8235. Min Range: -5.8235
Max Act: 5.5423. Min Act: -0.1700
Data Index: 6380803 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8235. Min Range: -5.8235
Max Act: 5.5735. Min Act: -0.1700
Data Index: 1830880 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19