Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5771 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4519. Min Range: -5.4519
Max Act: 5.4519. Min Act: -0.1700
Data Index: 7930165 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4519. Min Range: -5.4519
Max Act: 5.4206. Min Act: -0.1700
Data Index: 4638409 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4519. Min Range: -5.4519
Max Act: 5.4519. Min Act: -0.1700
Data Index: 7776135 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4519. Min Range: -5.4519
Max Act: 5.3894. Min Act: -0.1700
Data Index: 6782475 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4519. Min Range: -5.4519
Max Act: 5.3894. Min Act: -0.1700
Data Index: 6853357 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4519. Min Range: -5.4519
Max Act: 5.3894. Min Act: -0.1700
Data Index: 7087039 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4519. Min Range: -5.4519
Max Act: 5.3581. Min Act: -0.1700
Data Index: 8231454 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4519. Min Range: -5.4519
Max Act: 5.2956. Min Act: -0.1700
Data Index: 6076640 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4519. Min Range: -5.4519
Max Act: 5.2956. Min Act: -0.1700
Data Index: 1789947 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4519. Min Range: -5.4519
Max Act: 5.2644. Min Act: -0.1700
Data Index: 4800844 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4519. Min Range: -5.4519
Max Act: 5.2644. Min Act: -0.1700
Data Index: 7534609 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4519. Min Range: -5.4519
Max Act: 5.2644. Min Act: -0.1700
Data Index: 2817317 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4519. Min Range: -5.4519
Max Act: 5.2331. Min Act: -0.1700
Data Index: 528663 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4519. Min Range: -5.4519
Max Act: 5.2331. Min Act: -0.1700
Data Index: 4249482 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4519. Min Range: -5.4519
Max Act: 5.2019. Min Act: -0.1700
Data Index: 5989652 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4519. Min Range: -5.4519
Max Act: 5.2019. Min Act: -0.1700
Data Index: 1465319 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4519. Min Range: -5.4519
Max Act: 5.2019. Min Act: -0.1700
Data Index: 1941115 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4519. Min Range: -5.4519
Max Act: 5.2019. Min Act: -0.1700
Data Index: 1350015 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4519. Min Range: -5.4519
Max Act: 5.1706. Min Act: -0.1700
Data Index: 4042155 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4519. Min Range: -5.4519
Max Act: 5.1706. Min Act: -0.1700
Data Index: 2567792 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19