Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 188 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8046. Min Range: -5.8046
Max Act: 5.8046. Min Act: -0.1700
Data Index: 3323915 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8046. Min Range: -5.8046
Max Act: 5.7421. Min Act: -0.1700
Data Index: 693373 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8046. Min Range: -5.8046
Max Act: 5.7108. Min Act: -0.1700
Data Index: 4779000 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8046. Min Range: -5.8046
Max Act: 5.6796. Min Act: -0.1700
Data Index: 8685156 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8046. Min Range: -5.8046
Max Act: 5.6483. Min Act: -0.1700
Data Index: 2118106 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8046. Min Range: -5.8046
Max Act: 5.6483. Min Act: -0.1700
Data Index: 2644593 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8046. Min Range: -5.8046
Max Act: 5.5858. Min Act: -0.1700
Data Index: 6588225 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8046. Min Range: -5.8046
Max Act: 5.5858. Min Act: -0.1700
Data Index: 5542840 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8046. Min Range: -5.8046
Max Act: 5.5858. Min Act: -0.1700
Data Index: 7154920 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8046. Min Range: -5.8046
Max Act: 5.5546. Min Act: -0.1700
Data Index: 2182875 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8046. Min Range: -5.8046
Max Act: 5.4921. Min Act: -0.1700
Data Index: 921625 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8046. Min Range: -5.8046
Max Act: 5.4921. Min Act: -0.1700
Data Index: 5477589 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8046. Min Range: -5.8046
Max Act: 5.4921. Min Act: -0.1700
Data Index: 3110939 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8046. Min Range: -5.8046
Max Act: 5.4608. Min Act: -0.1700
Data Index: 655780 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8046. Min Range: -5.8046
Max Act: 5.4608. Min Act: -0.1700
Data Index: 7433345 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8046. Min Range: -5.8046
Max Act: 5.4608. Min Act: -0.1700
Data Index: 1564898 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8046. Min Range: -5.8046
Max Act: 5.4296. Min Act: -0.1700
Data Index: 884300 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8046. Min Range: -5.8046
Max Act: 5.4296. Min Act: -0.1700
Data Index: 3394003 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8046. Min Range: -5.8046
Max Act: 5.3983. Min Act: -0.1700
Data Index: 7455487 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8046. Min Range: -5.8046
Max Act: 5.3983. Min Act: -0.1700
Data Index: 5282216 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19