Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 663 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8684. Min Range: -5.8684
Max Act: 5.8684. Min Act: -0.1700
Data Index: 5647689 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8684. Min Range: -5.8684
Max Act: 5.8684. Min Act: -0.1700
Data Index: 2218393 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8684. Min Range: -5.8684
Max Act: 5.8059. Min Act: -0.1700
Data Index: 7497741 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8684. Min Range: -5.8684
Max Act: 5.7746. Min Act: -0.1700
Data Index: 6360957 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8684. Min Range: -5.8684
Max Act: 5.7746. Min Act: -0.1700
Data Index: 946413 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8684. Min Range: -5.8684
Max Act: 5.7121. Min Act: -0.1700
Data Index: 2898472 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8684. Min Range: -5.8684
Max Act: 5.6809. Min Act: -0.1700
Data Index: 6699550 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8684. Min Range: -5.8684
Max Act: 5.6496. Min Act: -0.1700
Data Index: 8831712 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8684. Min Range: -5.8684
Max Act: 5.6496. Min Act: -0.1700
Data Index: 313736 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8684. Min Range: -5.8684
Max Act: 5.5871. Min Act: -0.1700
Data Index: 427074 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8684. Min Range: -5.8684
Max Act: 5.6496. Min Act: -0.1700
Data Index: 6626638 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8684. Min Range: -5.8684
Max Act: 5.6184. Min Act: -0.1700
Data Index: 8005250 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8684. Min Range: -5.8684
Max Act: 5.6184. Min Act: -0.1700
Data Index: 879770 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8684. Min Range: -5.8684
Max Act: 5.5871. Min Act: -0.1700
Data Index: 1686948 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8684. Min Range: -5.8684
Max Act: 5.6184. Min Act: -0.1700
Data Index: 4644151 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8684. Min Range: -5.8684
Max Act: 5.5871. Min Act: -0.1700
Data Index: 4388819 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8684. Min Range: -5.8684
Max Act: 5.6496. Min Act: -0.1700
Data Index: 4325752 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8684. Min Range: -5.8684
Max Act: 5.5871. Min Act: -0.1700
Data Index: 578339 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8684. Min Range: -5.8684
Max Act: 5.5871. Min Act: -0.1700
Data Index: 2683258 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8684. Min Range: -5.8684
Max Act: 5.5871. Min Act: -0.1700
Data Index: 3376576 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19