Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1451 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1837. Min Range: -3.1837
Max Act: 3.1837. Min Act: -0.1700
Data Index: 6082113 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1837. Min Range: -3.1837
Max Act: 3.1679. Min Act: -0.1700
Data Index: 6487883 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1837. Min Range: -3.1837
Max Act: 3.1679. Min Act: -0.1700
Data Index: 6600656 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1837. Min Range: -3.1837
Max Act: 3.0576. Min Act: -0.1700
Data Index: 7307353 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1837. Min Range: -3.1837
Max Act: 3.0261. Min Act: -0.1700
Data Index: 4077431 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1837. Min Range: -3.1837
Max Act: 2.9786. Min Act: -0.1700
Data Index: 7426141 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1837. Min Range: -3.1837
Max Act: 2.9945. Min Act: -0.1700
Data Index: 2515904 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1837. Min Range: -3.1837
Max Act: 3.0103. Min Act: -0.1700
Data Index: 7216874 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1837. Min Range: -3.1837
Max Act: 2.9945. Min Act: -0.1700
Data Index: 6315427 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1837. Min Range: -3.1837
Max Act: 2.9786. Min Act: -0.1700
Data Index: 1000668 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1837. Min Range: -3.1837
Max Act: 2.9786. Min Act: -0.1700
Data Index: 4938347 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1837. Min Range: -3.1837
Max Act: 2.9470. Min Act: -0.1700
Data Index: 6072976 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1837. Min Range: -3.1837
Max Act: 2.9786. Min Act: -0.1700
Data Index: 5841971 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1837. Min Range: -3.1837
Max Act: 2.9470. Min Act: -0.1700
Data Index: 2817592 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1837. Min Range: -3.1837
Max Act: 2.9470. Min Act: -0.1700
Data Index: 6990943 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1837. Min Range: -3.1837
Max Act: 2.9470. Min Act: -0.1700
Data Index: 5905090 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1837. Min Range: -3.1837
Max Act: 2.9312. Min Act: -0.1700
Data Index: 385442 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1837. Min Range: -3.1837
Max Act: 2.9153. Min Act: -0.1700
Data Index: 3984460 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1837. Min Range: -3.1837
Max Act: 2.9470. Min Act: -0.1700
Data Index: 6580418 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1837. Min Range: -3.1837
Max Act: 2.9153. Min Act: -0.1700
Data Index: 6319968 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19