Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4092 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0765. Min Range: -3.0765
Max Act: 3.0765. Min Act: -0.1700
Data Index: 3215882 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0765. Min Range: -3.0765
Max Act: 3.0608. Min Act: -0.1700
Data Index: 5071825 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0765. Min Range: -3.0765
Max Act: 3.0608. Min Act: -0.1700
Data Index: 8614511 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0765. Min Range: -3.0765
Max Act: 3.0608. Min Act: -0.1700
Data Index: 3293014 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0765. Min Range: -3.0765
Max Act: 3.0765. Min Act: -0.1700
Data Index: 8034851 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0765. Min Range: -3.0765
Max Act: 3.0608. Min Act: -0.1700
Data Index: 2589212 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0765. Min Range: -3.0765
Max Act: 3.0608. Min Act: -0.1700
Data Index: 8826263 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0765. Min Range: -3.0765
Max Act: 3.0608. Min Act: -0.1700
Data Index: 3191489 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0765. Min Range: -3.0765
Max Act: 3.0608. Min Act: -0.1700
Data Index: 3108997 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0765. Min Range: -3.0765
Max Act: 3.0608. Min Act: -0.1700
Data Index: 7180226 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0765. Min Range: -3.0765
Max Act: 3.0292. Min Act: -0.1700
Data Index: 2150093 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0765. Min Range: -3.0765
Max Act: 3.0450. Min Act: -0.1700
Data Index: 227303 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0765. Min Range: -3.0765
Max Act: 3.0608. Min Act: -0.1700
Data Index: 1518134 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0765. Min Range: -3.0765
Max Act: 2.9976. Min Act: -0.1700
Data Index: 6652443 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0765. Min Range: -3.0765
Max Act: 3.0134. Min Act: -0.1700
Data Index: 5826372 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0765. Min Range: -3.0765
Max Act: 2.9660. Min Act: -0.1700
Data Index: 5841586 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0765. Min Range: -3.0765
Max Act: 2.9818. Min Act: -0.1700
Data Index: 1335052 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0765. Min Range: -3.0765
Max Act: 2.9502. Min Act: -0.1700
Data Index: 4368500 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0765. Min Range: -3.0765
Max Act: 2.9818. Min Act: -0.1700
Data Index: 8663077 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0765. Min Range: -3.0765
Max Act: 2.9660. Min Act: -0.1700
Data Index: 2814089 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19