Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 712 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1771. Min Range: -2.1771
Max Act: 2.1771. Min Act: -0.1700
Data Index: 8652519 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1771. Min Range: -2.1771
Max Act: 2.1104. Min Act: -0.1700
Data Index: 5724616 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1771. Min Range: -2.1771
Max Act: 2.1104. Min Act: -0.1700
Data Index: 2878505 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1771. Min Range: -2.1771
Max Act: 2.1104. Min Act: -0.1700
Data Index: 8180515 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1771. Min Range: -2.1771
Max Act: 2.0600. Min Act: -0.1700
Data Index: 5431444 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1771. Min Range: -2.1771
Max Act: 2.0432. Min Act: -0.1699
Data Index: 2174956 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1771. Min Range: -2.1771
Max Act: 2.0264. Min Act: -0.1700
Data Index: 1292471 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1771. Min Range: -2.1771
Max Act: 2.0264. Min Act: -0.1700
Data Index: 981283 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1771. Min Range: -2.1771
Max Act: 2.0264. Min Act: -0.1700
Data Index: 3426151 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1771. Min Range: -2.1771
Max Act: 2.0264. Min Act: -0.1700
Data Index: 2226875 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1771. Min Range: -2.1771
Max Act: 2.0095. Min Act: -0.1700
Data Index: 6310137 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1771. Min Range: -2.1771
Max Act: 2.0095. Min Act: -0.1700
Data Index: 3728133 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1771. Min Range: -2.1771
Max Act: 2.0095. Min Act: -0.1700
Data Index: 2579259 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1771. Min Range: -2.1771
Max Act: 2.0095. Min Act: -0.1700
Data Index: 6039019 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1771. Min Range: -2.1771
Max Act: 2.0095. Min Act: -0.1700
Data Index: 85022 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1771. Min Range: -2.1771
Max Act: 1.9926. Min Act: -0.1700
Data Index: 462869 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1771. Min Range: -2.1771
Max Act: 1.9926. Min Act: -0.1700
Data Index: 644220 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1771. Min Range: -2.1771
Max Act: 2.0095. Min Act: -0.1700
Data Index: 5463056 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1771. Min Range: -2.1771
Max Act: 2.0095. Min Act: -0.1700
Data Index: 5010326 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1771. Min Range: -2.1771
Max Act: 1.9926. Min Act: -0.1700
Data Index: 3224265 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19