Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5313 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6518. Min Range: -5.6518
Max Act: 5.6518. Min Act: -0.1700
Data Index: 2810399 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6518. Min Range: -5.6518
Max Act: 5.5268. Min Act: -0.1700
Data Index: 5302561 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6518. Min Range: -5.6518
Max Act: 5.3706. Min Act: -0.1700
Data Index: 5631105 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6518. Min Range: -5.6518
Max Act: 5.3393. Min Act: -0.1700
Data Index: 1361621 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6518. Min Range: -5.6518
Max Act: 5.3081. Min Act: -0.1700
Data Index: 7415516 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6518. Min Range: -5.6518
Max Act: 5.2768. Min Act: -0.1700
Data Index: 1792098 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6518. Min Range: -5.6518
Max Act: 5.2768. Min Act: -0.1700
Data Index: 2328112 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6518. Min Range: -5.6518
Max Act: 5.3081. Min Act: -0.1700
Data Index: 4986114 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6518. Min Range: -5.6518
Max Act: 5.2143. Min Act: -0.1700
Data Index: 6264478 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6518. Min Range: -5.6518
Max Act: 5.2143. Min Act: -0.1700
Data Index: 5050547 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6518. Min Range: -5.6518
Max Act: 5.1831. Min Act: -0.1700
Data Index: 2213610 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6518. Min Range: -5.6518
Max Act: 5.1831. Min Act: -0.1700
Data Index: 2312114 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6518. Min Range: -5.6518
Max Act: 5.1831. Min Act: -0.1700
Data Index: 5908420 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6518. Min Range: -5.6518
Max Act: 5.1518. Min Act: -0.1700
Data Index: 1373451 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6518. Min Range: -5.6518
Max Act: 5.1518. Min Act: -0.1700
Data Index: 6847111 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6518. Min Range: -5.6518
Max Act: 5.1518. Min Act: -0.1700
Data Index: 3870363 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6518. Min Range: -5.6518
Max Act: 5.1518. Min Act: -0.1700
Data Index: 3679504 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6518. Min Range: -5.6518
Max Act: 5.1518. Min Act: -0.1700
Data Index: 700511 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6518. Min Range: -5.6518
Max Act: 5.1206. Min Act: -0.1700
Data Index: 6275 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6518. Min Range: -5.6518
Max Act: 5.1206. Min Act: -0.1700
Data Index: 6220604 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19