Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2391 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8795. Min Range: -4.8795
Max Act: 4.8795. Min Act: -0.1700
Data Index: 3978276 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8795. Min Range: -4.8795
Max Act: 4.7858. Min Act: -0.1700
Data Index: 7295922 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8795. Min Range: -4.8795
Max Act: 4.7545. Min Act: -0.1700
Data Index: 1004913 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8795. Min Range: -4.8795
Max Act: 4.7545. Min Act: -0.1700
Data Index: 4687491 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8795. Min Range: -4.8795
Max Act: 4.7233. Min Act: -0.1700
Data Index: 3251633 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8795. Min Range: -4.8795
Max Act: 4.7233. Min Act: -0.1700
Data Index: 1233828 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8795. Min Range: -4.8795
Max Act: 4.7233. Min Act: -0.1700
Data Index: 3059066 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8795. Min Range: -4.8795
Max Act: 4.7233. Min Act: -0.1700
Data Index: 3728949 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8795. Min Range: -4.8795
Max Act: 4.6920. Min Act: -0.1700
Data Index: 1816810 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8795. Min Range: -4.8795
Max Act: 4.6920. Min Act: -0.1700
Data Index: 5153216 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8795. Min Range: -4.8795
Max Act: 4.6608. Min Act: -0.1700
Data Index: 2950197 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8795. Min Range: -4.8795
Max Act: 4.6295. Min Act: -0.1700
Data Index: 410109 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8795. Min Range: -4.8795
Max Act: 4.6295. Min Act: -0.1700
Data Index: 8569812 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8795. Min Range: -4.8795
Max Act: 4.5983. Min Act: -0.1700
Data Index: 2151299 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8795. Min Range: -4.8795
Max Act: 4.6295. Min Act: -0.1700
Data Index: 4807592 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8795. Min Range: -4.8795
Max Act: 4.5670. Min Act: -0.1700
Data Index: 4670828 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8795. Min Range: -4.8795
Max Act: 4.5983. Min Act: -0.1700
Data Index: 6869055 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8795. Min Range: -4.8795
Max Act: 4.6295. Min Act: -0.1700
Data Index: 4192571 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8795. Min Range: -4.8795
Max Act: 4.5983. Min Act: -0.1700
Data Index: 4721030 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8795. Min Range: -4.8795
Max Act: 4.6295. Min Act: -0.1700
Data Index: 8000386 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19