Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5054 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3843. Min Range: -8.3843
Max Act: 8.3843. Min Act: -0.1700
Data Index: 3912239 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3843. Min Range: -8.3843
Max Act: 8.2593. Min Act: -0.1700
Data Index: 4609071 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3843. Min Range: -8.3843
Max Act: 8.1343. Min Act: -0.1700
Data Index: 2773269 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3843. Min Range: -8.3843
Max Act: 8.1968. Min Act: -0.1700
Data Index: 2274965 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3843. Min Range: -8.3843
Max Act: 8.0718. Min Act: -0.1700
Data Index: 72546 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3843. Min Range: -8.3843
Max Act: 8.0718. Min Act: -0.1700
Data Index: 4513336 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3843. Min Range: -8.3843
Max Act: 8.0406. Min Act: -0.1700
Data Index: 8819802 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3843. Min Range: -8.3843
Max Act: 8.0406. Min Act: -0.1700
Data Index: 7939773 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3843. Min Range: -8.3843
Max Act: 8.0093. Min Act: -0.1700
Data Index: 8154872 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3843. Min Range: -8.3843
Max Act: 7.9156. Min Act: -0.1700
Data Index: 6758837 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3843. Min Range: -8.3843
Max Act: 7.9468. Min Act: -0.1700
Data Index: 1808671 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3843. Min Range: -8.3843
Max Act: 7.8843. Min Act: -0.1700
Data Index: 6548593 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3843. Min Range: -8.3843
Max Act: 7.8843. Min Act: -0.1700
Data Index: 6084194 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3843. Min Range: -8.3843
Max Act: 7.7906. Min Act: -0.1700
Data Index: 849807 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3843. Min Range: -8.3843
Max Act: 7.7906. Min Act: -0.1700
Data Index: 4337802 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3843. Min Range: -8.3843
Max Act: 7.7906. Min Act: -0.1700
Data Index: 7703001 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3843. Min Range: -8.3843
Max Act: 7.7281. Min Act: -0.1700
Data Index: 6625165 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3843. Min Range: -8.3843
Max Act: 7.7281. Min Act: -0.1700
Data Index: 5863357 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3843. Min Range: -8.3843
Max Act: 7.6968. Min Act: -0.1700
Data Index: 988253 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3843. Min Range: -8.3843
Max Act: 7.6968. Min Act: -0.1700
Data Index: 6523463 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19