Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2820 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4813. Min Range: -4.4813
Max Act: 4.4813. Min Act: -0.1700
Data Index: 1001833 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4813. Min Range: -4.4813
Max Act: 4.3875. Min Act: -0.1700
Data Index: 5982995 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4813. Min Range: -4.4813
Max Act: 4.3562. Min Act: -0.1700
Data Index: 8205971 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4813. Min Range: -4.4813
Max Act: 4.3250. Min Act: -0.1700
Data Index: 5921859 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4813. Min Range: -4.4813
Max Act: 4.2312. Min Act: -0.1700
Data Index: 4599216 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4813. Min Range: -4.4813
Max Act: 4.1687. Min Act: -0.1700
Data Index: 2393295 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4813. Min Range: -4.4813
Max Act: 4.2000. Min Act: -0.1700
Data Index: 1363955 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4813. Min Range: -4.4813
Max Act: 4.1375. Min Act: -0.1700
Data Index: 3627554 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4813. Min Range: -4.4813
Max Act: 4.1375. Min Act: -0.1700
Data Index: 6893744 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4813. Min Range: -4.4813
Max Act: 4.1375. Min Act: -0.1700
Data Index: 6196783 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4813. Min Range: -4.4813
Max Act: 4.1062. Min Act: -0.1700
Data Index: 7907054 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4813. Min Range: -4.4813
Max Act: 4.1062. Min Act: -0.1700
Data Index: 5725008 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4813. Min Range: -4.4813
Max Act: 4.1062. Min Act: -0.1700
Data Index: 5404730 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4813. Min Range: -4.4813
Max Act: 4.0750. Min Act: -0.1700
Data Index: 7372105 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4813. Min Range: -4.4813
Max Act: 4.1062. Min Act: -0.1700
Data Index: 1073948 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4813. Min Range: -4.4813
Max Act: 4.0750. Min Act: -0.1700
Data Index: 8302609 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4813. Min Range: -4.4813
Max Act: 4.1062. Min Act: -0.1700
Data Index: 4439807 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4813. Min Range: -4.4813
Max Act: 4.1062. Min Act: -0.1700
Data Index: 2838229 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4813. Min Range: -4.4813
Max Act: 4.0750. Min Act: -0.1700
Data Index: 4267853 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4813. Min Range: -4.4813
Max Act: 4.0437. Min Act: -0.1700
Data Index: 7803313 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19