Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2999 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9597. Min Range: -5.9597
Max Act: 5.9597. Min Act: -0.1700
Data Index: 6412517 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9597. Min Range: -5.9597
Max Act: 5.9284. Min Act: -0.1700
Data Index: 1445487 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9597. Min Range: -5.9597
Max Act: 5.9284. Min Act: -0.1700
Data Index: 5063508 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9597. Min Range: -5.9597
Max Act: 5.8972. Min Act: -0.1700
Data Index: 6879261 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9597. Min Range: -5.9597
Max Act: 5.8659. Min Act: -0.1699
Data Index: 2672758 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9597. Min Range: -5.9597
Max Act: 5.8659. Min Act: -0.1700
Data Index: 6377914 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9597. Min Range: -5.9597
Max Act: 5.8659. Min Act: -0.1700
Data Index: 8344121 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9597. Min Range: -5.9597
Max Act: 5.8347. Min Act: -0.1700
Data Index: 6233247 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9597. Min Range: -5.9597
Max Act: 5.8034. Min Act: -0.1700
Data Index: 650122 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9597. Min Range: -5.9597
Max Act: 5.8347. Min Act: -0.1700
Data Index: 267331 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9597. Min Range: -5.9597
Max Act: 5.8347. Min Act: -0.1700
Data Index: 8089352 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9597. Min Range: -5.9597
Max Act: 5.8347. Min Act: -0.1700
Data Index: 7757153 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9597. Min Range: -5.9597
Max Act: 5.8347. Min Act: -0.1700
Data Index: 1704251 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9597. Min Range: -5.9597
Max Act: 5.8034. Min Act: -0.1700
Data Index: 3728226 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9597. Min Range: -5.9597
Max Act: 5.8034. Min Act: -0.1700
Data Index: 1581608 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9597. Min Range: -5.9597
Max Act: 5.8034. Min Act: -0.1698
Data Index: 3911157 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9597. Min Range: -5.9597
Max Act: 5.7722. Min Act: -0.1699
Data Index: 5511974 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9597. Min Range: -5.9597
Max Act: 5.8034. Min Act: -0.1700
Data Index: 2817161 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9597. Min Range: -5.9597
Max Act: 5.7722. Min Act: -0.1700
Data Index: 1338028 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9597. Min Range: -5.9597
Max Act: 5.7722. Min Act: -0.1700
Data Index: 5725901 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19