Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2068 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2856. Min Range: -6.2856
Max Act: 6.2856. Min Act: -0.1700
Data Index: 8088130 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2856. Min Range: -6.2856
Max Act: 5.7856. Min Act: -0.1700
Data Index: 4326249 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2856. Min Range: -6.2856
Max Act: 5.7231. Min Act: -0.1700
Data Index: 1236602 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2856. Min Range: -6.2856
Max Act: 5.6606. Min Act: -0.1700
Data Index: 1670770 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2856. Min Range: -6.2856
Max Act: 5.5669. Min Act: -0.1700
Data Index: 5927805 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2856. Min Range: -6.2856
Max Act: 5.4419. Min Act: -0.1700
Data Index: 7619278 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2856. Min Range: -6.2856
Max Act: 5.4731. Min Act: -0.1700
Data Index: 1900930 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2856. Min Range: -6.2856
Max Act: 5.4419. Min Act: -0.1700
Data Index: 5199693 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2856. Min Range: -6.2856
Max Act: 5.4731. Min Act: -0.1700
Data Index: 5217617 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2856. Min Range: -6.2856
Max Act: 5.4419. Min Act: -0.1700
Data Index: 4090033 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2856. Min Range: -6.2856
Max Act: 5.4419. Min Act: -0.1700
Data Index: 3853357 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2856. Min Range: -6.2856
Max Act: 5.4419. Min Act: -0.1700
Data Index: 3165726 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2856. Min Range: -6.2856
Max Act: 5.4106. Min Act: -0.1700
Data Index: 6021198 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2856. Min Range: -6.2856
Max Act: 5.4106. Min Act: -0.1700
Data Index: 834319 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2856. Min Range: -6.2856
Max Act: 5.4106. Min Act: -0.1700
Data Index: 1684951 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2856. Min Range: -6.2856
Max Act: 5.3794. Min Act: -0.1700
Data Index: 1008514 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2856. Min Range: -6.2856
Max Act: 5.3794. Min Act: -0.1700
Data Index: 1030297 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2856. Min Range: -6.2856
Max Act: 5.3794. Min Act: -0.1700
Data Index: 4208154 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2856. Min Range: -6.2856
Max Act: 5.3794. Min Act: -0.1700
Data Index: 5834366 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2856. Min Range: -6.2856
Max Act: 5.3794. Min Act: -0.1700
Data Index: 1086763 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19