Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3321 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7849. Min Range: -3.7849
Max Act: 3.7849. Min Act: -0.1700
Data Index: 584352 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7849. Min Range: -3.7849
Max Act: 3.7224. Min Act: -0.1700
Data Index: 4455461 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7849. Min Range: -3.7849
Max Act: 3.7224. Min Act: -0.1700
Data Index: 7585925 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7849. Min Range: -3.7849
Max Act: 3.7537. Min Act: -0.1700
Data Index: 8599869 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7849. Min Range: -3.7849
Max Act: 3.6285. Min Act: -0.1700
Data Index: 1028800 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7849. Min Range: -3.7849
Max Act: 3.6598. Min Act: -0.1700
Data Index: 3262712 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7849. Min Range: -3.7849
Max Act: 3.6285. Min Act: -0.1700
Data Index: 2439164 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7849. Min Range: -3.7849
Max Act: 3.6285. Min Act: -0.1700
Data Index: 564850 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7849. Min Range: -3.7849
Max Act: 3.6285. Min Act: -0.1700
Data Index: 352415 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7849. Min Range: -3.7849
Max Act: 3.6285. Min Act: -0.1700
Data Index: 4729735 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7849. Min Range: -3.7849
Max Act: 3.6285. Min Act: -0.1700
Data Index: 7862820 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7849. Min Range: -3.7849
Max Act: 3.6285. Min Act: -0.1700
Data Index: 1939221 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7849. Min Range: -3.7849
Max Act: 3.5972. Min Act: -0.1700
Data Index: 6467078 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7849. Min Range: -3.7849
Max Act: 3.5972. Min Act: -0.1700
Data Index: 6677094 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7849. Min Range: -3.7849
Max Act: 3.5972. Min Act: -0.1700
Data Index: 4031038 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7849. Min Range: -3.7849
Max Act: 3.5972. Min Act: -0.1700
Data Index: 6179221 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7849. Min Range: -3.7849
Max Act: 3.5972. Min Act: -0.1700
Data Index: 3793354 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7849. Min Range: -3.7849
Max Act: 3.5816. Min Act: -0.1700
Data Index: 8100228 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7849. Min Range: -3.7849
Max Act: 3.5659. Min Act: -0.1700
Data Index: 8305537 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7849. Min Range: -3.7849
Max Act: 3.5659. Min Act: -0.1700
Data Index: 2377676 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19