Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 370 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4931. Min Range: -4.4931
Max Act: 4.4931. Min Act: -0.1700
Data Index: 2900287 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4931. Min Range: -4.4931
Max Act: 4.3681. Min Act: -0.1700
Data Index: 3292588 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4931. Min Range: -4.4931
Max Act: 4.3368. Min Act: -0.1700
Data Index: 2066097 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4931. Min Range: -4.4931
Max Act: 4.3368. Min Act: -0.1700
Data Index: 611676 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4931. Min Range: -4.4931
Max Act: 4.3368. Min Act: -0.1700
Data Index: 8810247 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4931. Min Range: -4.4931
Max Act: 4.3056. Min Act: -0.1700
Data Index: 6385475 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4931. Min Range: -4.4931
Max Act: 4.0868. Min Act: -0.1700
Data Index: 3503956 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4931. Min Range: -4.4931
Max Act: 4.0243. Min Act: -0.1700
Data Index: 5653196 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4931. Min Range: -4.4931
Max Act: 4.0555. Min Act: -0.1700
Data Index: 1972922 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4931. Min Range: -4.4931
Max Act: 4.0555. Min Act: -0.1700
Data Index: 1120987 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4931. Min Range: -4.4931
Max Act: 4.0555. Min Act: -0.1700
Data Index: 973194 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4931. Min Range: -4.4931
Max Act: 4.0555. Min Act: -0.1700
Data Index: 5983384 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4931. Min Range: -4.4931
Max Act: 3.9930. Min Act: -0.1700
Data Index: 7681242 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4931. Min Range: -4.4931
Max Act: 3.9930. Min Act: -0.1700
Data Index: 1440424 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4931. Min Range: -4.4931
Max Act: 4.0243. Min Act: -0.1700
Data Index: 2521593 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4931. Min Range: -4.4931
Max Act: 3.9617. Min Act: -0.1700
Data Index: 386314 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4931. Min Range: -4.4931
Max Act: 3.9617. Min Act: -0.1700
Data Index: 572900 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4931. Min Range: -4.4931
Max Act: 3.9305. Min Act: -0.1700
Data Index: 6055307 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4931. Min Range: -4.4931
Max Act: 3.9305. Min Act: -0.1700
Data Index: 4774355 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4931. Min Range: -4.4931
Max Act: 3.9305. Min Act: -0.1700
Data Index: 7385690 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19