Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3203 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6627. Min Range: -6.6627
Max Act: 6.6627. Min Act: -0.1700
Data Index: 8041316 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6627. Min Range: -6.6627
Max Act: 6.3502. Min Act: -0.1700
Data Index: 4934696 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6627. Min Range: -6.6627
Max Act: 6.2564. Min Act: -0.1700
Data Index: 2062807 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6627. Min Range: -6.6627
Max Act: 6.1939. Min Act: -0.1700
Data Index: 4013814 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6627. Min Range: -6.6627
Max Act: 6.1627. Min Act: -0.1700
Data Index: 3956950 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6627. Min Range: -6.6627
Max Act: 6.1002. Min Act: -0.1700
Data Index: 4738339 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6627. Min Range: -6.6627
Max Act: 6.1002. Min Act: -0.1700
Data Index: 4365354 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6627. Min Range: -6.6627
Max Act: 6.1002. Min Act: -0.1700
Data Index: 6321150 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6627. Min Range: -6.6627
Max Act: 6.0689. Min Act: -0.1700
Data Index: 2425069 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6627. Min Range: -6.6627
Max Act: 6.0689. Min Act: -0.1700
Data Index: 3253305 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6627. Min Range: -6.6627
Max Act: 6.0689. Min Act: -0.1700
Data Index: 6391347 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6627. Min Range: -6.6627
Max Act: 6.0689. Min Act: -0.1700
Data Index: 6365770 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6627. Min Range: -6.6627
Max Act: 6.1002. Min Act: -0.1700
Data Index: 304260 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6627. Min Range: -6.6627
Max Act: 6.0689. Min Act: -0.1700
Data Index: 7837115 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6627. Min Range: -6.6627
Max Act: 6.0377. Min Act: -0.1700
Data Index: 4485009 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6627. Min Range: -6.6627
Max Act: 6.0064. Min Act: -0.1700
Data Index: 886733 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6627. Min Range: -6.6627
Max Act: 6.0377. Min Act: -0.1700
Data Index: 3639045 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6627. Min Range: -6.6627
Max Act: 6.0064. Min Act: -0.1700
Data Index: 1583455 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6627. Min Range: -6.6627
Max Act: 6.0064. Min Act: -0.1700
Data Index: 8766546 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6627. Min Range: -6.6627
Max Act: 5.9752. Min Act: -0.1700
Data Index: 3895337 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19