Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3890 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9504. Min Range: -4.9504
Max Act: 4.9504. Min Act: -0.1700
Data Index: 4060869 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9504. Min Range: -4.9504
Max Act: 4.9504. Min Act: -0.1700
Data Index: 4440573 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9504. Min Range: -4.9504
Max Act: 4.8567. Min Act: -0.1700
Data Index: 4304626 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9504. Min Range: -4.9504
Max Act: 4.8567. Min Act: -0.1700
Data Index: 7807546 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9504. Min Range: -4.9504
Max Act: 4.8567. Min Act: -0.1700
Data Index: 2332560 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9504. Min Range: -4.9504
Max Act: 4.8879. Min Act: -0.1700
Data Index: 7537495 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9504. Min Range: -4.9504
Max Act: 4.8567. Min Act: -0.1700
Data Index: 7237138 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9504. Min Range: -4.9504
Max Act: 4.8254. Min Act: -0.1700
Data Index: 7394518 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9504. Min Range: -4.9504
Max Act: 4.8254. Min Act: -0.1700
Data Index: 3833621 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9504. Min Range: -4.9504
Max Act: 4.8254. Min Act: -0.1700
Data Index: 1173092 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9504. Min Range: -4.9504
Max Act: 4.8254. Min Act: -0.1700
Data Index: 935325 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9504. Min Range: -4.9504
Max Act: 4.8254. Min Act: -0.1700
Data Index: 2555154 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9504. Min Range: -4.9504
Max Act: 4.7942. Min Act: -0.1700
Data Index: 4974598 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9504. Min Range: -4.9504
Max Act: 4.8254. Min Act: -0.1700
Data Index: 4046417 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9504. Min Range: -4.9504
Max Act: 4.7942. Min Act: -0.1700
Data Index: 982392 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9504. Min Range: -4.9504
Max Act: 4.7942. Min Act: -0.1700
Data Index: 3519500 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9504. Min Range: -4.9504
Max Act: 4.7942. Min Act: -0.1700
Data Index: 5126525 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9504. Min Range: -4.9504
Max Act: 4.7629. Min Act: -0.1700
Data Index: 6238360 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9504. Min Range: -4.9504
Max Act: 4.7629. Min Act: -0.1700
Data Index: 3170490 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9504. Min Range: -4.9504
Max Act: 4.7629. Min Act: -0.1700
Data Index: 4093860 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19