Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3512 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3937. Min Range: -9.3937
Max Act: 9.3937. Min Act: -0.1700
Data Index: 1225414 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3937. Min Range: -9.3937
Max Act: 8.8937. Min Act: -0.1700
Data Index: 2721137 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3937. Min Range: -9.3937
Max Act: 8.8312. Min Act: -0.1700
Data Index: 8113709 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3937. Min Range: -9.3937
Max Act: 8.6437. Min Act: -0.1700
Data Index: 6733358 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3937. Min Range: -9.3937
Max Act: 8.6437. Min Act: -0.1700
Data Index: 2690412 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3937. Min Range: -9.3937
Max Act: 8.5187. Min Act: -0.1700
Data Index: 3426714 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3937. Min Range: -9.3937
Max Act: 8.4562. Min Act: -0.1700
Data Index: 3746597 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3937. Min Range: -9.3937
Max Act: 8.5187. Min Act: -0.1700
Data Index: 8508602 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3937. Min Range: -9.3937
Max Act: 8.3937. Min Act: -0.1700
Data Index: 6094214 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3937. Min Range: -9.3937
Max Act: 8.4562. Min Act: -0.1700
Data Index: 7617703 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3937. Min Range: -9.3937
Max Act: 8.3937. Min Act: -0.1700
Data Index: 6754207 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3937. Min Range: -9.3937
Max Act: 8.3937. Min Act: -0.1700
Data Index: 7257709 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3937. Min Range: -9.3937
Max Act: 8.3312. Min Act: -0.1700
Data Index: 7207024 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3937. Min Range: -9.3937
Max Act: 8.3312. Min Act: -0.1700
Data Index: 3095987 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3937. Min Range: -9.3937
Max Act: 8.3312. Min Act: -0.1700
Data Index: 30793 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3937. Min Range: -9.3937
Max Act: 8.3937. Min Act: -0.1700
Data Index: 883550 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3937. Min Range: -9.3937
Max Act: 8.3312. Min Act: -0.1700
Data Index: 7151857 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3937. Min Range: -9.3937
Max Act: 8.3312. Min Act: -0.1700
Data Index: 3585137 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3937. Min Range: -9.3937
Max Act: 8.3312. Min Act: -0.1700
Data Index: 455951 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3937. Min Range: -9.3937
Max Act: 8.2687. Min Act: -0.1700
Data Index: 5467202 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19