Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 550 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0749. Min Range: -5.0749
Max Act: 5.0749. Min Act: -0.1700
Data Index: 1242250 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.8874. Min Act: -0.1700
Data Index: 1700874 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.8249. Min Act: -0.1700
Data Index: 2371907 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.8249. Min Act: -0.1700
Data Index: 3881044 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.8249. Min Act: -0.1700
Data Index: 8133358 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.7937. Min Act: -0.1700
Data Index: 352645 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.7937. Min Act: -0.1700
Data Index: 1708879 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.7937. Min Act: -0.1700
Data Index: 1242249 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.7937. Min Act: -0.1700
Data Index: 2207218 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.7624. Min Act: -0.1700
Data Index: 3519056 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.7312. Min Act: -0.1700
Data Index: 327274 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.7312. Min Act: -0.1700
Data Index: 492622 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.7312. Min Act: -0.1700
Data Index: 4477354 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.6999. Min Act: -0.1700
Data Index: 135185 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.6999. Min Act: -0.1700
Data Index: 7451072 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.6999. Min Act: -0.1700
Data Index: 7183108 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.6999. Min Act: -0.1700
Data Index: 1449729 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.6687. Min Act: -0.1700
Data Index: 5551463 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.6687. Min Act: -0.1700
Data Index: 6735033 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.6687. Min Act: -0.1700
Data Index: 7769807 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19