Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3273 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8185. Min Range: -7.8185
Max Act: 7.8185. Min Act: -0.1700
Data Index: 773563 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8185. Min Range: -7.8185
Max Act: 7.6622. Min Act: -0.1700
Data Index: 8032939 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8185. Min Range: -7.8185
Max Act: 7.6310. Min Act: -0.1700
Data Index: 6886365 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8185. Min Range: -7.8185
Max Act: 7.5372. Min Act: -0.1700
Data Index: 6508297 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8185. Min Range: -7.8185
Max Act: 7.4747. Min Act: -0.1700
Data Index: 2264632 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8185. Min Range: -7.8185
Max Act: 7.4122. Min Act: -0.1700
Data Index: 4213753 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8185. Min Range: -7.8185
Max Act: 7.4435. Min Act: -0.1700
Data Index: 3878715 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8185. Min Range: -7.8185
Max Act: 7.4435. Min Act: -0.1700
Data Index: 3745435 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8185. Min Range: -7.8185
Max Act: 7.4435. Min Act: -0.1700
Data Index: 2024613 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8185. Min Range: -7.8185
Max Act: 7.3810. Min Act: -0.1700
Data Index: 5899846 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8185. Min Range: -7.8185
Max Act: 7.3497. Min Act: -0.1700
Data Index: 5878081 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8185. Min Range: -7.8185
Max Act: 7.3810. Min Act: -0.1700
Data Index: 7333375 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8185. Min Range: -7.8185
Max Act: 7.3497. Min Act: -0.1700
Data Index: 1159163 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8185. Min Range: -7.8185
Max Act: 7.3497. Min Act: -0.1700
Data Index: 3538292 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8185. Min Range: -7.8185
Max Act: 7.3185. Min Act: -0.1700
Data Index: 4418023 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8185. Min Range: -7.8185
Max Act: 7.2872. Min Act: -0.1700
Data Index: 1234382 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8185. Min Range: -7.8185
Max Act: 7.2872. Min Act: -0.1700
Data Index: 6840915 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8185. Min Range: -7.8185
Max Act: 7.2872. Min Act: -0.1700
Data Index: 677674 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8185. Min Range: -7.8185
Max Act: 7.2560. Min Act: -0.1700
Data Index: 6423237 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8185. Min Range: -7.8185
Max Act: 7.2560. Min Act: -0.1700
Data Index: 2858486 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19