Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2557 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.0844. Min Range: -9.0844
Max Act: 9.0844. Min Act: -0.1700
Data Index: 6732551 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0844. Min Range: -9.0844
Max Act: 8.4282. Min Act: -0.1700
Data Index: 1368308 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0844. Min Range: -9.0844
Max Act: 8.3032. Min Act: -0.1700
Data Index: 6865534 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0844. Min Range: -9.0844
Max Act: 8.2719. Min Act: -0.1700
Data Index: 5985331 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0844. Min Range: -9.0844
Max Act: 8.3032. Min Act: -0.1700
Data Index: 7380539 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0844. Min Range: -9.0844
Max Act: 8.2719. Min Act: -0.1700
Data Index: 8066604 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0844. Min Range: -9.0844
Max Act: 8.2719. Min Act: -0.1700
Data Index: 8435458 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0844. Min Range: -9.0844
Max Act: 8.2094. Min Act: -0.1700
Data Index: 7705085 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0844. Min Range: -9.0844
Max Act: 8.2094. Min Act: -0.1700
Data Index: 4317855 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0844. Min Range: -9.0844
Max Act: 8.2407. Min Act: -0.1700
Data Index: 5487558 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0844. Min Range: -9.0844
Max Act: 8.2719. Min Act: -0.1700
Data Index: 4121653 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0844. Min Range: -9.0844
Max Act: 8.2094. Min Act: -0.1700
Data Index: 4264580 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0844. Min Range: -9.0844
Max Act: 8.2407. Min Act: -0.1700
Data Index: 2059477 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0844. Min Range: -9.0844
Max Act: 8.2094. Min Act: -0.1700
Data Index: 6617075 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0844. Min Range: -9.0844
Max Act: 8.1782. Min Act: -0.1700
Data Index: 3343935 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0844. Min Range: -9.0844
Max Act: 8.1469. Min Act: -0.1700
Data Index: 4103247 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0844. Min Range: -9.0844
Max Act: 8.1782. Min Act: -0.1700
Data Index: 7565584 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0844. Min Range: -9.0844
Max Act: 8.0532. Min Act: -0.1700
Data Index: 508855 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0844. Min Range: -9.0844
Max Act: 8.0532. Min Act: -0.1700
Data Index: 4682927 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0844. Min Range: -9.0844
Max Act: 8.1469. Min Act: -0.1700
Data Index: 6798286 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19