Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 371 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.3695. Min Act: -0.1700
Data Index: 7096976 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.3695. Min Act: -0.1700
Data Index: 5852324 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.3383. Min Act: -0.1700
Data Index: 7723543 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.3383. Min Act: -0.1700
Data Index: 6190387 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.3383. Min Act: -0.1700
Data Index: 895599 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.3383. Min Act: -0.1700
Data Index: 3060006 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.3070. Min Act: -0.1700
Data Index: 1414604 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.3383. Min Act: -0.1700
Data Index: 8828201 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.3383. Min Act: -0.1700
Data Index: 8475314 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.3070. Min Act: -0.1700
Data Index: 1427144 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.3070. Min Act: -0.1700
Data Index: 4229219 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.3070. Min Act: -0.1700
Data Index: 6036130 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.3070. Min Act: -0.1700
Data Index: 1681842 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.3070. Min Act: -0.1700
Data Index: 8342974 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.2758. Min Act: -0.1700
Data Index: 2955719 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.2758. Min Act: -0.1700
Data Index: 5748815 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.2758. Min Act: -0.1700
Data Index: 66388 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.2758. Min Act: -0.1700
Data Index: 106 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.2758. Min Act: -0.1700
Data Index: 266121 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.2758. Min Act: -0.1700
Data Index: 1759911 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19