Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3708 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6452. Min Range: -5.6452
Max Act: 5.6452. Min Act: -0.1700
Data Index: 542482 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6452. Min Range: -5.6452
Max Act: 5.6139. Min Act: -0.1700
Data Index: 589239 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6452. Min Range: -5.6452
Max Act: 5.3327. Min Act: -0.1700
Data Index: 3133862 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6452. Min Range: -5.6452
Max Act: 5.2702. Min Act: -0.1700
Data Index: 1196256 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6452. Min Range: -5.6452
Max Act: 5.2702. Min Act: -0.1700
Data Index: 8629655 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6452. Min Range: -5.6452
Max Act: 5.3014. Min Act: -0.1700
Data Index: 2908456 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6452. Min Range: -5.6452
Max Act: 5.2702. Min Act: -0.1700
Data Index: 7398683 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6452. Min Range: -5.6452
Max Act: 5.2077. Min Act: -0.1700
Data Index: 2726697 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6452. Min Range: -5.6452
Max Act: 5.2077. Min Act: -0.1700
Data Index: 5502686 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6452. Min Range: -5.6452
Max Act: 5.2077. Min Act: -0.1700
Data Index: 1134476 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6452. Min Range: -5.6452
Max Act: 5.1764. Min Act: -0.1700
Data Index: 4558914 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6452. Min Range: -5.6452
Max Act: 5.1452. Min Act: -0.1700
Data Index: 6166367 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6452. Min Range: -5.6452
Max Act: 5.1139. Min Act: -0.1700
Data Index: 1125435 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6452. Min Range: -5.6452
Max Act: 5.1452. Min Act: -0.1700
Data Index: 2853948 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6452. Min Range: -5.6452
Max Act: 5.1139. Min Act: -0.1700
Data Index: 1015601 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6452. Min Range: -5.6452
Max Act: 5.0827. Min Act: -0.1700
Data Index: 7902733 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6452. Min Range: -5.6452
Max Act: 5.0827. Min Act: -0.1700
Data Index: 6162546 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6452. Min Range: -5.6452
Max Act: 5.0827. Min Act: -0.1700
Data Index: 1759508 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6452. Min Range: -5.6452
Max Act: 5.0827. Min Act: -0.1700
Data Index: 722312 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6452. Min Range: -5.6452
Max Act: 5.0827. Min Act: -0.1700
Data Index: 7091274 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19