Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2895 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6333. Min Range: -6.6333
Max Act: 6.6333. Min Act: -0.1700
Data Index: 6855391 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6333. Min Range: -6.6333
Max Act: 6.4146. Min Act: -0.1700
Data Index: 677362 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6333. Min Range: -6.6333
Max Act: 6.3833. Min Act: -0.1700
Data Index: 4148693 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6333. Min Range: -6.6333
Max Act: 6.3208. Min Act: -0.1700
Data Index: 4229911 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6333. Min Range: -6.6333
Max Act: 6.2896. Min Act: -0.1700
Data Index: 4286195 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6333. Min Range: -6.6333
Max Act: 6.2896. Min Act: -0.1700
Data Index: 6714788 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6333. Min Range: -6.6333
Max Act: 6.2896. Min Act: -0.1700
Data Index: 6714787 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6333. Min Range: -6.6333
Max Act: 6.2271. Min Act: -0.1700
Data Index: 4229910 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6333. Min Range: -6.6333
Max Act: 6.2271. Min Act: -0.1700
Data Index: 6445877 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6333. Min Range: -6.6333
Max Act: 6.1958. Min Act: -0.1700
Data Index: 6575204 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6333. Min Range: -6.6333
Max Act: 6.1646. Min Act: -0.1700
Data Index: 8386220 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6333. Min Range: -6.6333
Max Act: 6.1646. Min Act: -0.1700
Data Index: 1067446 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6333. Min Range: -6.6333
Max Act: 6.1646. Min Act: -0.1700
Data Index: 3122679 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6333. Min Range: -6.6333
Max Act: 6.1646. Min Act: -0.1700
Data Index: 4229909 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6333. Min Range: -6.6333
Max Act: 6.1333. Min Act: -0.1700
Data Index: 7878812 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6333. Min Range: -6.6333
Max Act: 6.1333. Min Act: -0.1700
Data Index: 4041605 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6333. Min Range: -6.6333
Max Act: 6.0708. Min Act: -0.1700
Data Index: 8319049 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6333. Min Range: -6.6333
Max Act: 6.0708. Min Act: -0.1700
Data Index: 5363385 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6333. Min Range: -6.6333
Max Act: 6.0083. Min Act: -0.1700
Data Index: 2327345 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6333. Min Range: -6.6333
Max Act: 6.0083. Min Act: -0.1700
Data Index: 1763664 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19