Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3561 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7521. Min Range: -5.7521
Max Act: 5.7521. Min Act: -0.1700
Data Index: 2334743 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7521. Min Range: -5.7521
Max Act: 5.6896. Min Act: -0.1700
Data Index: 802758 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7521. Min Range: -5.7521
Max Act: 5.6583. Min Act: -0.1700
Data Index: 802767 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7521. Min Range: -5.7521
Max Act: 5.5021. Min Act: -0.1700
Data Index: 3984205 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7521. Min Range: -5.7521
Max Act: 5.4396. Min Act: -0.1700
Data Index: 6900256 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7521. Min Range: -5.7521
Max Act: 5.4083. Min Act: -0.1700
Data Index: 936000 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7521. Min Range: -5.7521
Max Act: 5.4083. Min Act: -0.1700
Data Index: 4484985 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7521. Min Range: -5.7521
Max Act: 5.3771. Min Act: -0.1700
Data Index: 4484982 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7521. Min Range: -5.7521
Max Act: 5.3458. Min Act: -0.1700
Data Index: 2508383 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7521. Min Range: -5.7521
Max Act: 5.3458. Min Act: -0.1700
Data Index: 8267807 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7521. Min Range: -5.7521
Max Act: 5.2521. Min Act: -0.1700
Data Index: 8166362 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7521. Min Range: -5.7521
Max Act: 5.2208. Min Act: -0.1700
Data Index: 4700880 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7521. Min Range: -5.7521
Max Act: 5.1896. Min Act: -0.1700
Data Index: 775091 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7521. Min Range: -5.7521
Max Act: 5.1896. Min Act: -0.1700
Data Index: 5724070 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7521. Min Range: -5.7521
Max Act: 5.2208. Min Act: -0.1700
Data Index: 3929019 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7521. Min Range: -5.7521
Max Act: 5.1271. Min Act: -0.1700
Data Index: 6200354 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7521. Min Range: -5.7521
Max Act: 5.0958. Min Act: -0.1700
Data Index: 8166361 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7521. Min Range: -5.7521
Max Act: 5.0958. Min Act: -0.1700
Data Index: 802768 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7521. Min Range: -5.7521
Max Act: 5.0646. Min Act: -0.1700
Data Index: 3047541 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7521. Min Range: -5.7521
Max Act: 5.0646. Min Act: -0.1700
Data Index: 3209 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19