Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3246 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3780. Min Range: -5.3780
Max Act: 5.3780. Min Act: -0.1700
Data Index: 7648881 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3780. Min Range: -5.3780
Max Act: 5.2218. Min Act: -0.1700
Data Index: 8599733 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3780. Min Range: -5.3780
Max Act: 5.2530. Min Act: -0.1700
Data Index: 2543762 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3780. Min Range: -5.3780
Max Act: 5.2218. Min Act: -0.1700
Data Index: 8732682 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3780. Min Range: -5.3780
Max Act: 5.1905. Min Act: -0.1700
Data Index: 4514185 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3780. Min Range: -5.3780
Max Act: 5.0968. Min Act: -0.1700
Data Index: 5607260 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3780. Min Range: -5.3780
Max Act: 5.0968. Min Act: -0.1700
Data Index: 3454835 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3780. Min Range: -5.3780
Max Act: 5.0655. Min Act: -0.1700
Data Index: 7621729 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3780. Min Range: -5.3780
Max Act: 5.0655. Min Act: -0.1700
Data Index: 2190402 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3780. Min Range: -5.3780
Max Act: 5.0655. Min Act: -0.1700
Data Index: 6250869 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3780. Min Range: -5.3780
Max Act: 5.0343. Min Act: -0.1700
Data Index: 5909397 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3780. Min Range: -5.3780
Max Act: 5.0343. Min Act: -0.1700
Data Index: 2116014 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3780. Min Range: -5.3780
Max Act: 5.0343. Min Act: -0.1700
Data Index: 1839591 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3780. Min Range: -5.3780
Max Act: 5.0030. Min Act: -0.1700
Data Index: 1418196 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3780. Min Range: -5.3780
Max Act: 5.0030. Min Act: -0.1700
Data Index: 4233932 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3780. Min Range: -5.3780
Max Act: 5.0030. Min Act: -0.1700
Data Index: 7550887 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3780. Min Range: -5.3780
Max Act: 4.9718. Min Act: -0.1700
Data Index: 5711671 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3780. Min Range: -5.3780
Max Act: 5.0030. Min Act: -0.1700
Data Index: 3804584 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3780. Min Range: -5.3780
Max Act: 4.9718. Min Act: -0.1700
Data Index: 7002290 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3780. Min Range: -5.3780
Max Act: 4.9718. Min Act: -0.1700
Data Index: 3050198 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19