Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2991 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3753. Min Range: -5.3753
Max Act: 5.3753. Min Act: -0.1700
Data Index: 7892026 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3753. Min Range: -5.3753
Max Act: 5.3753. Min Act: -0.1700
Data Index: 1046353 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3753. Min Range: -5.3753
Max Act: 5.3753. Min Act: -0.1700
Data Index: 6520924 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3753. Min Range: -5.3753
Max Act: 5.3441. Min Act: -0.1700
Data Index: 4581988 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3753. Min Range: -5.3753
Max Act: 5.3753. Min Act: -0.1700
Data Index: 4581645 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3753. Min Range: -5.3753
Max Act: 5.3128. Min Act: -0.1700
Data Index: 6349352 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3753. Min Range: -5.3753
Max Act: 5.3128. Min Act: -0.1700
Data Index: 123732 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3753. Min Range: -5.3753
Max Act: 5.3128. Min Act: -0.1700
Data Index: 5689049 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3753. Min Range: -5.3753
Max Act: 5.3128. Min Act: -0.1700
Data Index: 4001441 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3753. Min Range: -5.3753
Max Act: 5.3128. Min Act: -0.1700
Data Index: 5153019 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3753. Min Range: -5.3753
Max Act: 5.2816. Min Act: -0.1700
Data Index: 1703757 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3753. Min Range: -5.3753
Max Act: 5.2816. Min Act: -0.1700
Data Index: 6957800 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3753. Min Range: -5.3753
Max Act: 5.3128. Min Act: -0.1700
Data Index: 2596225 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3753. Min Range: -5.3753
Max Act: 5.2503. Min Act: -0.1700
Data Index: 1643089 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3753. Min Range: -5.3753
Max Act: 5.2503. Min Act: -0.1700
Data Index: 6696063 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3753. Min Range: -5.3753
Max Act: 5.2191. Min Act: -0.1700
Data Index: 4951436 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3753. Min Range: -5.3753
Max Act: 5.2191. Min Act: -0.1700
Data Index: 4435837 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3753. Min Range: -5.3753
Max Act: 5.2191. Min Act: -0.1700
Data Index: 59575 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3753. Min Range: -5.3753
Max Act: 5.1878. Min Act: -0.1700
Data Index: 1902190 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3753. Min Range: -5.3753
Max Act: 5.1878. Min Act: -0.1700
Data Index: 2433699 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19