Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2945 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.5767. Min Act: -0.1700
Data Index: 3201596 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3887. Min Act: -0.1700
Data Index: 4769396 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3416. Min Act: -0.1700
Data Index: 8523901 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3259. Min Act: -0.1700
Data Index: 5423828 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3416. Min Act: -0.1700
Data Index: 3139351 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3573. Min Act: -0.1700
Data Index: 7731152 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3416. Min Act: -0.1700
Data Index: 1883595 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3259. Min Act: -0.1700
Data Index: 6007015 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3102. Min Act: -0.1700
Data Index: 4634568 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3259. Min Act: -0.1700
Data Index: 2612023 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3102. Min Act: -0.1700
Data Index: 3714703 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.2945. Min Act: -0.1700
Data Index: 2177111 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3102. Min Act: -0.1700
Data Index: 7033590 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3102. Min Act: -0.1700
Data Index: 6565986 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.2945. Min Act: -0.1700
Data Index: 6402377 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3259. Min Act: -0.1700
Data Index: 6194162 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3102. Min Act: -0.1700
Data Index: 6021830 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.2788. Min Act: -0.1700
Data Index: 777081 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.2788. Min Act: -0.1700
Data Index: 3254252 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.2788. Min Act: -0.1700
Data Index: 727648 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19