Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3276 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6499. Min Range: -5.6499
Max Act: 5.6499. Min Act: -0.1700
Data Index: 59339 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6499. Min Range: -5.6499
Max Act: 5.3999. Min Act: -0.1700
Data Index: 2764123 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6499. Min Range: -5.6499
Max Act: 5.3687. Min Act: -0.1700
Data Index: 716942 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6499. Min Range: -5.6499
Max Act: 5.3687. Min Act: -0.1700
Data Index: 1715952 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6499. Min Range: -5.6499
Max Act: 5.2749. Min Act: -0.1700
Data Index: 6924622 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6499. Min Range: -5.6499
Max Act: 5.1812. Min Act: -0.1700
Data Index: 8372030 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6499. Min Range: -5.6499
Max Act: 5.1812. Min Act: -0.1700
Data Index: 303368 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6499. Min Range: -5.6499
Max Act: 5.1499. Min Act: -0.1700
Data Index: 7237177 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6499. Min Range: -5.6499
Max Act: 5.1499. Min Act: -0.1700
Data Index: 16797 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6499. Min Range: -5.6499
Max Act: 5.1499. Min Act: -0.1700
Data Index: 3560082 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6499. Min Range: -5.6499
Max Act: 5.1499. Min Act: -0.1700
Data Index: 8290961 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6499. Min Range: -5.6499
Max Act: 5.1187. Min Act: -0.1700
Data Index: 3535882 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6499. Min Range: -5.6499
Max Act: 5.1187. Min Act: -0.1700
Data Index: 1360951 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6499. Min Range: -5.6499
Max Act: 5.0874. Min Act: -0.1700
Data Index: 7356814 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6499. Min Range: -5.6499
Max Act: 5.0562. Min Act: -0.1700
Data Index: 1779842 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6499. Min Range: -5.6499
Max Act: 5.0874. Min Act: -0.1700
Data Index: 4398428 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6499. Min Range: -5.6499
Max Act: 5.0249. Min Act: -0.1700
Data Index: 7114530 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6499. Min Range: -5.6499
Max Act: 5.0562. Min Act: -0.1700
Data Index: 8112560 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6499. Min Range: -5.6499
Max Act: 5.0562. Min Act: -0.1700
Data Index: 8508447 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6499. Min Range: -5.6499
Max Act: 5.0562. Min Act: -0.1700
Data Index: 7659 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19