Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1546 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.7907. Min Act: -0.1700
Data Index: 5356045 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.7595. Min Act: -0.1700
Data Index: 6339697 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.7282. Min Act: -0.1700
Data Index: 259056 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.7438. Min Act: -0.1700
Data Index: 129504 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.6813. Min Act: -0.1700
Data Index: 2498795 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.6813. Min Act: -0.1700
Data Index: 7233359 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.6656. Min Act: -0.1700
Data Index: 4183667 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.6813. Min Act: -0.1700
Data Index: 4198713 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.6500. Min Act: -0.1700
Data Index: 5563152 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.6656. Min Act: -0.1700
Data Index: 2471610 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.6187. Min Act: -0.1700
Data Index: 738447 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.6030. Min Act: -0.1700
Data Index: 1406300 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.6030. Min Act: -0.1700
Data Index: 3129785 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.5874. Min Act: -0.1700
Data Index: 7541525 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.5874. Min Act: -0.1700
Data Index: 6400461 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.5404. Min Act: -0.1700
Data Index: 1484996 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.5561. Min Act: -0.1700
Data Index: 3302805 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.5561. Min Act: -0.1700
Data Index: 1634989 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.5404. Min Act: -0.1700
Data Index: 202959 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.5247. Min Act: -0.1700
Data Index: 3133431 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19