Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1958 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7666. Min Range: -4.7666
Max Act: 4.7666. Min Act: -0.1700
Data Index: 5709025 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7666. Min Range: -4.7666
Max Act: 4.7353. Min Act: -0.1700
Data Index: 3244783 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7666. Min Range: -4.7666
Max Act: 4.7041. Min Act: -0.1700
Data Index: 1056347 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7666. Min Range: -4.7666
Max Act: 4.7041. Min Act: -0.1700
Data Index: 4121209 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7666. Min Range: -4.7666
Max Act: 4.7041. Min Act: -0.1700
Data Index: 1435369 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7666. Min Range: -4.7666
Max Act: 4.6728. Min Act: -0.1700
Data Index: 3762452 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7666. Min Range: -4.7666
Max Act: 4.6728. Min Act: -0.1700
Data Index: 8154122 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7666. Min Range: -4.7666
Max Act: 4.7041. Min Act: -0.1700
Data Index: 3284720 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7666. Min Range: -4.7666
Max Act: 4.6416. Min Act: -0.1700
Data Index: 5797288 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7666. Min Range: -4.7666
Max Act: 4.6416. Min Act: -0.1700
Data Index: 893171 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7666. Min Range: -4.7666
Max Act: 4.6416. Min Act: -0.1700
Data Index: 1495776 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7666. Min Range: -4.7666
Max Act: 4.6728. Min Act: -0.1700
Data Index: 3015878 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7666. Min Range: -4.7666
Max Act: 4.6103. Min Act: -0.1700
Data Index: 2043473 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7666. Min Range: -4.7666
Max Act: 4.6103. Min Act: -0.1700
Data Index: 5991873 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7666. Min Range: -4.7666
Max Act: 4.6103. Min Act: -0.1700
Data Index: 3529628 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7666. Min Range: -4.7666
Max Act: 4.6103. Min Act: -0.1700
Data Index: 5509095 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7666. Min Range: -4.7666
Max Act: 4.5478. Min Act: -0.1700
Data Index: 1494906 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7666. Min Range: -4.7666
Max Act: 4.5791. Min Act: -0.1700
Data Index: 35886 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7666. Min Range: -4.7666
Max Act: 4.5791. Min Act: -0.1700
Data Index: 370607 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7666. Min Range: -4.7666
Max Act: 4.6103. Min Act: -0.1699
Data Index: 883902 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19