Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2263 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0255. Min Range: -3.0255
Max Act: 3.0255. Min Act: -0.1700
Data Index: 4620874 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0255. Min Range: -3.0255
Max Act: 2.9781. Min Act: -0.1700
Data Index: 4250763 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0255. Min Range: -3.0255
Max Act: 2.9306. Min Act: -0.1700
Data Index: 3014975 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0255. Min Range: -3.0255
Max Act: 2.9306. Min Act: -0.1700
Data Index: 2303764 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0255. Min Range: -3.0255
Max Act: 2.9148. Min Act: -0.1700
Data Index: 2201873 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0255. Min Range: -3.0255
Max Act: 2.8989. Min Act: -0.1700
Data Index: 2370161 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0255. Min Range: -3.0255
Max Act: 2.8989. Min Act: -0.1700
Data Index: 2674580 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0255. Min Range: -3.0255
Max Act: 2.8831. Min Act: -0.1700
Data Index: 5140619 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0255. Min Range: -3.0255
Max Act: 2.8513. Min Act: -0.1700
Data Index: 2559753 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0255. Min Range: -3.0255
Max Act: 2.8195. Min Act: -0.1700
Data Index: 1684133 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0255. Min Range: -3.0255
Max Act: 2.8195. Min Act: -0.1700
Data Index: 3336809 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0255. Min Range: -3.0255
Max Act: 2.8195. Min Act: -0.1700
Data Index: 1810935 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0255. Min Range: -3.0255
Max Act: 2.8036. Min Act: -0.1700
Data Index: 3498923 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0255. Min Range: -3.0255
Max Act: 2.8036. Min Act: -0.1700
Data Index: 2886543 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0255. Min Range: -3.0255
Max Act: 2.7877. Min Act: -0.1700
Data Index: 774890 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0255. Min Range: -3.0255
Max Act: 2.8036. Min Act: -0.1700
Data Index: 7999513 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0255. Min Range: -3.0255
Max Act: 2.8036. Min Act: -0.1700
Data Index: 5238776 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0255. Min Range: -3.0255
Max Act: 2.7877. Min Act: -0.1700
Data Index: 4062774 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0255. Min Range: -3.0255
Max Act: 2.7717. Min Act: -0.1700
Data Index: 2652511 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0255. Min Range: -3.0255
Max Act: 2.7877. Min Act: -0.1700
Data Index: 7287429 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19