Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3495 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8820. Min Range: -6.8820
Max Act: 6.8820. Min Act: -0.1700
Data Index: 6437485 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8820. Min Range: -6.8820
Max Act: 6.8820. Min Act: -0.1700
Data Index: 3584707 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8820. Min Range: -6.8820
Max Act: 6.8820. Min Act: -0.1700
Data Index: 7830689 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8820. Min Range: -6.8820
Max Act: 6.8820. Min Act: -0.1700
Data Index: 6426855 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8820. Min Range: -6.8820
Max Act: 6.8820. Min Act: -0.1700
Data Index: 2389543 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8820. Min Range: -6.8820
Max Act: 6.8820. Min Act: -0.1700
Data Index: 2407538 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8820. Min Range: -6.8820
Max Act: 6.8507. Min Act: -0.1700
Data Index: 2804849 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8820. Min Range: -6.8820
Max Act: 6.8820. Min Act: -0.1700
Data Index: 6428238 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8820. Min Range: -6.8820
Max Act: 6.8507. Min Act: -0.1700
Data Index: 7701073 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8820. Min Range: -6.8820
Max Act: 6.8507. Min Act: -0.1700
Data Index: 1322707 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8820. Min Range: -6.8820
Max Act: 6.8507. Min Act: -0.1700
Data Index: 4543016 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8820. Min Range: -6.8820
Max Act: 6.8507. Min Act: -0.1700
Data Index: 624551 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8820. Min Range: -6.8820
Max Act: 6.8195. Min Act: -0.1700
Data Index: 5431242 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8820. Min Range: -6.8820
Max Act: 6.8195. Min Act: -0.1700
Data Index: 4909924 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8820. Min Range: -6.8820
Max Act: 6.8195. Min Act: -0.1700
Data Index: 2503155 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8820. Min Range: -6.8820
Max Act: 6.8195. Min Act: -0.1700
Data Index: 4548742 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8820. Min Range: -6.8820
Max Act: 6.7882. Min Act: -0.1700
Data Index: 1352471 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8820. Min Range: -6.8820
Max Act: 6.8195. Min Act: -0.1700
Data Index: 2172631 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8820. Min Range: -6.8820
Max Act: 6.8195. Min Act: -0.1700
Data Index: 1910512 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8820. Min Range: -6.8820
Max Act: 6.8195. Min Act: -0.1700
Data Index: 1801956 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19