Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2921 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7488. Min Range: -5.7488
Max Act: 5.7488. Min Act: -0.1700
Data Index: 7771094 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7488. Min Range: -5.7488
Max Act: 5.3425. Min Act: -0.1700
Data Index: 5735131 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7488. Min Range: -5.7488
Max Act: 5.3425. Min Act: -0.1700
Data Index: 7739856 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7488. Min Range: -5.7488
Max Act: 5.2800. Min Act: -0.1700
Data Index: 5682722 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7488. Min Range: -5.7488
Max Act: 5.2488. Min Act: -0.1700
Data Index: 3699548 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7488. Min Range: -5.7488
Max Act: 5.2175. Min Act: -0.1700
Data Index: 3850379 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7488. Min Range: -5.7488
Max Act: 5.2488. Min Act: -0.1700
Data Index: 742687 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7488. Min Range: -5.7488
Max Act: 5.1863. Min Act: -0.1700
Data Index: 2443974 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7488. Min Range: -5.7488
Max Act: 5.1550. Min Act: -0.1700
Data Index: 2965185 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7488. Min Range: -5.7488
Max Act: 5.1238. Min Act: -0.1700
Data Index: 2145553 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7488. Min Range: -5.7488
Max Act: 5.1238. Min Act: -0.1700
Data Index: 6803608 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7488. Min Range: -5.7488
Max Act: 5.1238. Min Act: -0.1700
Data Index: 3237899 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7488. Min Range: -5.7488
Max Act: 5.0925. Min Act: -0.1700
Data Index: 8084284 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7488. Min Range: -5.7488
Max Act: 5.0925. Min Act: -0.1700
Data Index: 32048 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7488. Min Range: -5.7488
Max Act: 5.0613. Min Act: -0.1700
Data Index: 5372518 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7488. Min Range: -5.7488
Max Act: 5.0925. Min Act: -0.1700
Data Index: 8756238 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7488. Min Range: -5.7488
Max Act: 5.0925. Min Act: -0.1700
Data Index: 3276496 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7488. Min Range: -5.7488
Max Act: 5.0925. Min Act: -0.1700
Data Index: 7646322 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7488. Min Range: -5.7488
Max Act: 5.0925. Min Act: -0.1700
Data Index: 7288007 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7488. Min Range: -5.7488
Max Act: 5.0613. Min Act: -0.1700
Data Index: 613939 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19