Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2655 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9516. Min Range: -5.9516
Max Act: 5.9516. Min Act: -0.1700
Data Index: 5015028 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9516. Min Range: -5.9516
Max Act: 5.8891. Min Act: -0.1700
Data Index: 8768314 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9516. Min Range: -5.9516
Max Act: 5.8266. Min Act: -0.1700
Data Index: 5024395 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9516. Min Range: -5.9516
Max Act: 5.7953. Min Act: -0.1700
Data Index: 7346814 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9516. Min Range: -5.9516
Max Act: 5.7953. Min Act: -0.1700
Data Index: 5708489 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9516. Min Range: -5.9516
Max Act: 5.7953. Min Act: -0.1700
Data Index: 4904046 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9516. Min Range: -5.9516
Max Act: 5.7953. Min Act: -0.1700
Data Index: 2506958 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9516. Min Range: -5.9516
Max Act: 5.7953. Min Act: -0.1700
Data Index: 5520589 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9516. Min Range: -5.9516
Max Act: 5.7953. Min Act: -0.1700
Data Index: 7490053 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9516. Min Range: -5.9516
Max Act: 5.7953. Min Act: -0.1700
Data Index: 2200722 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9516. Min Range: -5.9516
Max Act: 5.7641. Min Act: -0.1700
Data Index: 5004873 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9516. Min Range: -5.9516
Max Act: 5.7641. Min Act: -0.1700
Data Index: 8655716 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9516. Min Range: -5.9516
Max Act: 5.7328. Min Act: -0.1700
Data Index: 2598244 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9516. Min Range: -5.9516
Max Act: 5.7328. Min Act: -0.1700
Data Index: 3913702 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9516. Min Range: -5.9516
Max Act: 5.7328. Min Act: -0.1700
Data Index: 8714475 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9516. Min Range: -5.9516
Max Act: 5.7016. Min Act: -0.1700
Data Index: 7699206 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9516. Min Range: -5.9516
Max Act: 5.7016. Min Act: -0.1700
Data Index: 2434430 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9516. Min Range: -5.9516
Max Act: 5.7016. Min Act: -0.1700
Data Index: 116245 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9516. Min Range: -5.9516
Max Act: 5.7016. Min Act: -0.1700
Data Index: 4726680 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9516. Min Range: -5.9516
Max Act: 5.7016. Min Act: -0.1700
Data Index: 712365 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19