Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2817 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.9564. Min Act: -0.1700
Data Index: 3036596 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.8939. Min Act: -0.1700
Data Index: 1526617 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.7689. Min Act: -0.1700
Data Index: 419132 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.7376. Min Act: -0.1700
Data Index: 8601616 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.7376. Min Act: -0.1700
Data Index: 3226469 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.6439. Min Act: -0.1700
Data Index: 4501711 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.6751. Min Act: -0.1700
Data Index: 3975714 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.6439. Min Act: -0.1700
Data Index: 7287956 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.5814. Min Act: -0.1700
Data Index: 5774643 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.5189. Min Act: -0.1700
Data Index: 5541601 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.4876. Min Act: -0.1700
Data Index: 2864362 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.4876. Min Act: -0.1700
Data Index: 6633124 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.5189. Min Act: -0.1700
Data Index: 3830078 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.5189. Min Act: -0.1700
Data Index: 8221249 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.5189. Min Act: -0.1700
Data Index: 7586440 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.5189. Min Act: -0.1700
Data Index: 7352253 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.4876. Min Act: -0.1700
Data Index: 640343 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.4876. Min Act: -0.1700
Data Index: 8536960 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.4876. Min Act: -0.1700
Data Index: 4160519 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.5189. Min Act: -0.1700
Data Index: 5966149 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19