Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5073 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5350. Min Range: -6.5350
Max Act: 6.5350. Min Act: -0.1700
Data Index: 4048363 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5350. Min Range: -6.5350
Max Act: 6.4413. Min Act: -0.1700
Data Index: 3896311 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5350. Min Range: -6.5350
Max Act: 6.3475. Min Act: -0.1700
Data Index: 5100493 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5350. Min Range: -6.5350
Max Act: 6.3475. Min Act: -0.1700
Data Index: 1871500 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5350. Min Range: -6.5350
Max Act: 6.3163. Min Act: -0.1700
Data Index: 5454970 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5350. Min Range: -6.5350
Max Act: 6.2850. Min Act: -0.1700
Data Index: 189865 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5350. Min Range: -6.5350
Max Act: 6.2538. Min Act: -0.1700
Data Index: 3816961 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5350. Min Range: -6.5350
Max Act: 6.2538. Min Act: -0.1700
Data Index: 7106119 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5350. Min Range: -6.5350
Max Act: 6.2538. Min Act: -0.1700
Data Index: 7444383 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5350. Min Range: -6.5350
Max Act: 6.2225. Min Act: -0.1700
Data Index: 2192557 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5350. Min Range: -6.5350
Max Act: 6.2225. Min Act: -0.1700
Data Index: 2137053 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5350. Min Range: -6.5350
Max Act: 6.2225. Min Act: -0.1700
Data Index: 5214681 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5350. Min Range: -6.5350
Max Act: 6.2225. Min Act: -0.1700
Data Index: 4687431 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5350. Min Range: -6.5350
Max Act: 6.1913. Min Act: -0.1700
Data Index: 6647200 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5350. Min Range: -6.5350
Max Act: 6.1913. Min Act: -0.1700
Data Index: 1635793 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5350. Min Range: -6.5350
Max Act: 6.1913. Min Act: -0.1700
Data Index: 6248865 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5350. Min Range: -6.5350
Max Act: 6.1913. Min Act: -0.1700
Data Index: 288290 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5350. Min Range: -6.5350
Max Act: 6.1913. Min Act: -0.1700
Data Index: 8352819 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5350. Min Range: -6.5350
Max Act: 6.1913. Min Act: -0.1700
Data Index: 6157302 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5350. Min Range: -6.5350
Max Act: 6.1600. Min Act: -0.1700
Data Index: 2137062 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19