Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2106 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.3637. Min Act: -0.1700
Data Index: 2931975 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.3637. Min Act: -0.1700
Data Index: 4612836 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.3012. Min Act: -0.1700
Data Index: 6257367 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.2700. Min Act: -0.1700
Data Index: 1001207 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.2700. Min Act: -0.1700
Data Index: 6395757 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.1762. Min Act: -0.1700
Data Index: 1798770 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.1762. Min Act: -0.1700
Data Index: 4537900 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.1762. Min Act: -0.1700
Data Index: 7244903 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.1450. Min Act: -0.1700
Data Index: 1853331 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.1137. Min Act: -0.1700
Data Index: 2445302 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.1137. Min Act: -0.1700
Data Index: 4684495 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.0825. Min Act: -0.1700
Data Index: 354180 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.0512. Min Act: -0.1700
Data Index: 2096408 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.0512. Min Act: -0.1700
Data Index: 1507811 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.0200. Min Act: -0.1700
Data Index: 134366 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.0200. Min Act: -0.1700
Data Index: 3005045 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3637. Min Range: -5.3637
Max Act: 4.9575. Min Act: -0.1700
Data Index: 6206617 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3637. Min Range: -5.3637
Max Act: 4.9575. Min Act: -0.1700
Data Index: 3304295 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3637. Min Range: -5.3637
Max Act: 4.9887. Min Act: -0.1700
Data Index: 5143577 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3637. Min Range: -5.3637
Max Act: 4.9575. Min Act: -0.1700
Data Index: 1212138 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19