Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 73 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5413. Min Range: -5.5413
Max Act: 5.5413. Min Act: -0.1700
Data Index: 4759690 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5413. Min Range: -5.5413
Max Act: 5.4163. Min Act: -0.1700
Data Index: 6762269 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5413. Min Range: -5.5413
Max Act: 5.3850. Min Act: -0.1700
Data Index: 8495568 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5413. Min Range: -5.5413
Max Act: 5.3538. Min Act: -0.1700
Data Index: 1867143 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5413. Min Range: -5.5413
Max Act: 5.2913. Min Act: -0.1700
Data Index: 8631101 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5413. Min Range: -5.5413
Max Act: 5.3225. Min Act: -0.1700
Data Index: 1949383 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5413. Min Range: -5.5413
Max Act: 5.2600. Min Act: -0.1700
Data Index: 2080936 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5413. Min Range: -5.5413
Max Act: 5.1975. Min Act: -0.1700
Data Index: 3237938 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5413. Min Range: -5.5413
Max Act: 5.1975. Min Act: -0.1700
Data Index: 6908386 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5413. Min Range: -5.5413
Max Act: 5.1975. Min Act: -0.1700
Data Index: 1287233 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5413. Min Range: -5.5413
Max Act: 5.1975. Min Act: -0.1700
Data Index: 5789298 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5413. Min Range: -5.5413
Max Act: 5.1350. Min Act: -0.1700
Data Index: 3113245 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5413. Min Range: -5.5413
Max Act: 5.1350. Min Act: -0.1700
Data Index: 3583129 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5413. Min Range: -5.5413
Max Act: 5.1350. Min Act: -0.1700
Data Index: 3264193 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5413. Min Range: -5.5413
Max Act: 5.1350. Min Act: -0.1700
Data Index: 2830174 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5413. Min Range: -5.5413
Max Act: 5.1350. Min Act: -0.1700
Data Index: 3671522 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5413. Min Range: -5.5413
Max Act: 5.1038. Min Act: -0.1700
Data Index: 7049792 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5413. Min Range: -5.5413
Max Act: 5.1038. Min Act: -0.1700
Data Index: 7083615 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5413. Min Range: -5.5413
Max Act: 5.1038. Min Act: -0.1700
Data Index: 4699615 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5413. Min Range: -5.5413
Max Act: 5.0725. Min Act: -0.1700
Data Index: 3861760 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19