Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1490 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9830. Min Range: -2.9830
Max Act: 2.9830. Min Act: -0.1700
Data Index: 1594197 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9830. Min Range: -2.9830
Max Act: 2.9514. Min Act: -0.1700
Data Index: 2611043 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9830. Min Range: -2.9830
Max Act: 2.8880. Min Act: -0.1700
Data Index: 3964792 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9830. Min Range: -2.9830
Max Act: 2.9039. Min Act: -0.1700
Data Index: 8391138 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9830. Min Range: -2.9830
Max Act: 2.8721. Min Act: -0.1700
Data Index: 4219274 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9830. Min Range: -2.9830
Max Act: 2.8404. Min Act: -0.1700
Data Index: 6966071 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9830. Min Range: -2.9830
Max Act: 2.8721. Min Act: -0.1700
Data Index: 237022 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9830. Min Range: -2.9830
Max Act: 2.8404. Min Act: -0.1700
Data Index: 2160017 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9830. Min Range: -2.9830
Max Act: 2.8562. Min Act: -0.1700
Data Index: 6428278 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9830. Min Range: -2.9830
Max Act: 2.8085. Min Act: -0.1700
Data Index: 6106084 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9830. Min Range: -2.9830
Max Act: 2.8245. Min Act: -0.1700
Data Index: 4950643 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9830. Min Range: -2.9830
Max Act: 2.8245. Min Act: -0.1700
Data Index: 8789286 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9830. Min Range: -2.9830
Max Act: 2.8085. Min Act: -0.1700
Data Index: 5373154 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9830. Min Range: -2.9830
Max Act: 2.7767. Min Act: -0.1700
Data Index: 860778 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9830. Min Range: -2.9830
Max Act: 2.7926. Min Act: -0.1700
Data Index: 1847382 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9830. Min Range: -2.9830
Max Act: 2.7926. Min Act: -0.1700
Data Index: 8783905 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9830. Min Range: -2.9830
Max Act: 2.7926. Min Act: -0.1700
Data Index: 2530900 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9830. Min Range: -2.9830
Max Act: 2.7607. Min Act: -0.1700
Data Index: 2752391 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9830. Min Range: -2.9830
Max Act: 2.7926. Min Act: -0.1700
Data Index: 6000894 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9830. Min Range: -2.9830
Max Act: 2.7607. Min Act: -0.1700
Data Index: 924485 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19