Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4087 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.6707. Min Act: -0.1700
Data Index: 8444323 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.6707. Min Act: -0.1700
Data Index: 7821248 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.6707. Min Act: -0.1700
Data Index: 895774 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.6707. Min Act: -0.1700
Data Index: 7227680 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.6395. Min Act: -0.1700
Data Index: 3732275 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.6082. Min Act: -0.1700
Data Index: 4880794 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.6082. Min Act: -0.1700
Data Index: 7043072 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.5770. Min Act: -0.1700
Data Index: 4880795 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.5457. Min Act: -0.1700
Data Index: 4334494 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.5457. Min Act: -0.1700
Data Index: 6134069 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.5457. Min Act: -0.1700
Data Index: 1234424 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.5145. Min Act: -0.1700
Data Index: 5019703 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.5145. Min Act: -0.1700
Data Index: 3825459 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.5145. Min Act: -0.1700
Data Index: 4232264 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.5457. Min Act: -0.1700
Data Index: 8652198 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.4832. Min Act: -0.1700
Data Index: 5558944 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.4832. Min Act: -0.1700
Data Index: 7358526 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.4832. Min Act: -0.1700
Data Index: 6393213 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.5145. Min Act: -0.1700
Data Index: 1549083 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6707. Min Range: -4.6707
Max Act: 4.4520. Min Act: -0.1700
Data Index: 1502840 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19