Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 858 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6769. Min Range: -5.6769
Max Act: 5.6769. Min Act: -0.1700
Data Index: 5785507 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6769. Min Range: -5.6769
Max Act: 5.6144. Min Act: -0.1700
Data Index: 5885303 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6769. Min Range: -5.6769
Max Act: 5.4581. Min Act: -0.1700
Data Index: 826974 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6769. Min Range: -5.6769
Max Act: 5.4581. Min Act: -0.1700
Data Index: 7758983 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6769. Min Range: -5.6769
Max Act: 5.4581. Min Act: -0.1700
Data Index: 7705483 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6769. Min Range: -5.6769
Max Act: 5.4269. Min Act: -0.1700
Data Index: 1896345 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6769. Min Range: -5.6769
Max Act: 5.4269. Min Act: -0.1700
Data Index: 7440776 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6769. Min Range: -5.6769
Max Act: 5.3956. Min Act: -0.1700
Data Index: 8814395 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6769. Min Range: -5.6769
Max Act: 5.3956. Min Act: -0.1700
Data Index: 826975 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6769. Min Range: -5.6769
Max Act: 5.3956. Min Act: -0.1700
Data Index: 826973 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6769. Min Range: -5.6769
Max Act: 5.3956. Min Act: -0.1700
Data Index: 826980 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6769. Min Range: -5.6769
Max Act: 5.3644. Min Act: -0.1700
Data Index: 826981 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6769. Min Range: -5.6769
Max Act: 5.3644. Min Act: -0.1700
Data Index: 5648393 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6769. Min Range: -5.6769
Max Act: 5.3331. Min Act: -0.1700
Data Index: 5785506 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6769. Min Range: -5.6769
Max Act: 5.3331. Min Act: -0.1700
Data Index: 6361386 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6769. Min Range: -5.6769
Max Act: 5.3019. Min Act: -0.1700
Data Index: 2581151 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6769. Min Range: -5.6769
Max Act: 5.3019. Min Act: -0.1700
Data Index: 8699095 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6769. Min Range: -5.6769
Max Act: 5.2394. Min Act: -0.1700
Data Index: 4527048 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6769. Min Range: -5.6769
Max Act: 5.2706. Min Act: -0.1700
Data Index: 8374039 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6769. Min Range: -5.6769
Max Act: 5.2706. Min Act: -0.1700
Data Index: 6010153 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19