Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3208 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.4619. Min Act: -0.1700
Data Index: 3338204 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.4931. Min Act: -0.1700
Data Index: 3382072 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.4306. Min Act: -0.1700
Data Index: 4441312 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.3681. Min Act: -0.1700
Data Index: 6257969 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.3369. Min Act: -0.1700
Data Index: 113246 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.3369. Min Act: -0.1700
Data Index: 7480207 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.3056. Min Act: -0.1700
Data Index: 6238321 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.3056. Min Act: -0.1700
Data Index: 3458006 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.2744. Min Act: -0.1700
Data Index: 841651 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.2744. Min Act: -0.1700
Data Index: 2715426 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.2744. Min Act: -0.1700
Data Index: 3138285 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.2744. Min Act: -0.1700
Data Index: 5851881 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.2431. Min Act: -0.1700
Data Index: 6039356 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.2431. Min Act: -0.1700
Data Index: 2399535 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.2431. Min Act: -0.1700
Data Index: 6785568 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.2119. Min Act: -0.1700
Data Index: 5031109 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.1806. Min Act: -0.1700
Data Index: 6645371 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.2119. Min Act: -0.1700
Data Index: 8699385 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.2119. Min Act: -0.1700
Data Index: 7585585 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.1806. Min Act: -0.1700
Data Index: 6891966 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19