Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3864 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2798. Min Range: -5.2798
Max Act: 5.2798. Min Act: -0.1700
Data Index: 3774445 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2798. Min Range: -5.2798
Max Act: 5.2486. Min Act: -0.1694
Data Index: 4032639 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2798. Min Range: -5.2798
Max Act: 5.2486. Min Act: -0.1700
Data Index: 8137444 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2798. Min Range: -5.2798
Max Act: 5.1861. Min Act: -0.1700
Data Index: 4792852 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2798. Min Range: -5.2798
Max Act: 5.1861. Min Act: -0.1694
Data Index: 170364 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2798. Min Range: -5.2798
Max Act: 5.1861. Min Act: -0.1700
Data Index: 163080 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2798. Min Range: -5.2798
Max Act: 5.1548. Min Act: -0.1694
Data Index: 3127999 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2798. Min Range: -5.2798
Max Act: 5.1236. Min Act: -0.1697
Data Index: 1353033 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2798. Min Range: -5.2798
Max Act: 5.1548. Min Act: -0.1699
Data Index: 1242820 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2798. Min Range: -5.2798
Max Act: 5.1236. Min Act: -0.1698
Data Index: 4588260 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2798. Min Range: -5.2798
Max Act: 5.1236. Min Act: -0.1700
Data Index: 4164116 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2798. Min Range: -5.2798
Max Act: 5.1236. Min Act: -0.1692
Data Index: 3225030 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2798. Min Range: -5.2798
Max Act: 5.1236. Min Act: -0.1700
Data Index: 520237 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2798. Min Range: -5.2798
Max Act: 5.1236. Min Act: -0.1700
Data Index: 1949593 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2798. Min Range: -5.2798
Max Act: 5.1548. Min Act: -0.1700
Data Index: 2931186 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2798. Min Range: -5.2798
Max Act: 5.1236. Min Act: -0.1700
Data Index: 2423148 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2798. Min Range: -5.2798
Max Act: 5.1236. Min Act: -0.1700
Data Index: 1961502 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2798. Min Range: -5.2798
Max Act: 5.1236. Min Act: -0.1698
Data Index: 1135110 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2798. Min Range: -5.2798
Max Act: 5.1236. Min Act: -0.1694
Data Index: 1978642 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2798. Min Range: -5.2798
Max Act: 5.1236. Min Act: -0.1700
Data Index: 639307 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19