Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4898 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7901. Min Range: -5.7901
Max Act: 5.7901. Min Act: -0.1700
Data Index: 4486638 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7901. Min Range: -5.7901
Max Act: 5.7901. Min Act: -0.1700
Data Index: 5355818 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7901. Min Range: -5.7901
Max Act: 5.6339. Min Act: -0.1700
Data Index: 3114179 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7901. Min Range: -5.7901
Max Act: 5.6026. Min Act: -0.1700
Data Index: 3160028 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7901. Min Range: -5.7901
Max Act: 5.6026. Min Act: -0.1700
Data Index: 5733163 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7901. Min Range: -5.7901
Max Act: 5.6026. Min Act: -0.1700
Data Index: 3872237 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7901. Min Range: -5.7901
Max Act: 5.5714. Min Act: -0.1700
Data Index: 3163421 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7901. Min Range: -5.7901
Max Act: 5.5401. Min Act: -0.1700
Data Index: 7391536 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7901. Min Range: -5.7901
Max Act: 5.5089. Min Act: -0.1700
Data Index: 5820192 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7901. Min Range: -5.7901
Max Act: 5.5401. Min Act: -0.1700
Data Index: 2403281 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7901. Min Range: -5.7901
Max Act: 5.4776. Min Act: -0.1700
Data Index: 6971411 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7901. Min Range: -5.7901
Max Act: 5.4464. Min Act: -0.1700
Data Index: 7589255 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7901. Min Range: -5.7901
Max Act: 5.4464. Min Act: -0.1700
Data Index: 7792672 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7901. Min Range: -5.7901
Max Act: 5.4464. Min Act: -0.1700
Data Index: 8706765 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7901. Min Range: -5.7901
Max Act: 5.4464. Min Act: -0.1700
Data Index: 6616581 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7901. Min Range: -5.7901
Max Act: 5.3839. Min Act: -0.1700
Data Index: 7331204 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7901. Min Range: -5.7901
Max Act: 5.3526. Min Act: -0.1700
Data Index: 671275 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7901. Min Range: -5.7901
Max Act: 5.3526. Min Act: -0.1700
Data Index: 4970880 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7901. Min Range: -5.7901
Max Act: 5.3839. Min Act: -0.1700
Data Index: 7512854 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7901. Min Range: -5.7901
Max Act: 5.3526. Min Act: -0.1700
Data Index: 3943753 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19