Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5894 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8997. Min Range: -5.8997
Max Act: 5.8997. Min Act: -0.1700
Data Index: 1049825 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8997. Min Range: -5.8997
Max Act: 5.8372. Min Act: -0.1700
Data Index: 6313885 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8997. Min Range: -5.8997
Max Act: 5.7747. Min Act: -0.1700
Data Index: 7630944 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8997. Min Range: -5.8997
Max Act: 5.8059. Min Act: -0.1700
Data Index: 1869731 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8997. Min Range: -5.8997
Max Act: 5.6809. Min Act: -0.1700
Data Index: 1166124 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8997. Min Range: -5.8997
Max Act: 5.6809. Min Act: -0.1700
Data Index: 5984274 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8997. Min Range: -5.8997
Max Act: 5.5872. Min Act: -0.1700
Data Index: 762252 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8997. Min Range: -5.8997
Max Act: 5.5872. Min Act: -0.1700
Data Index: 3632016 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8997. Min Range: -5.8997
Max Act: 5.6184. Min Act: -0.1700
Data Index: 5770108 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8997. Min Range: -5.8997
Max Act: 5.5559. Min Act: -0.1700
Data Index: 7132028 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8997. Min Range: -5.8997
Max Act: 5.5247. Min Act: -0.1700
Data Index: 601682 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8997. Min Range: -5.8997
Max Act: 5.4934. Min Act: -0.1700
Data Index: 4569810 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8997. Min Range: -5.8997
Max Act: 5.4622. Min Act: -0.1700
Data Index: 8569908 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8997. Min Range: -5.8997
Max Act: 5.4622. Min Act: -0.1700
Data Index: 6637521 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8997. Min Range: -5.8997
Max Act: 5.4622. Min Act: -0.1700
Data Index: 4537793 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8997. Min Range: -5.8997
Max Act: 5.4622. Min Act: -0.1700
Data Index: 7830667 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8997. Min Range: -5.8997
Max Act: 5.4309. Min Act: -0.1700
Data Index: 6728211 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8997. Min Range: -5.8997
Max Act: 5.3684. Min Act: -0.1700
Data Index: 6308108 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8997. Min Range: -5.8997
Max Act: 5.3684. Min Act: -0.1700
Data Index: 8777790 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8997. Min Range: -5.8997
Max Act: 5.3684. Min Act: -0.1700
Data Index: 2504106 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19