Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1999 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5999. Min Range: -7.5999
Max Act: 7.5999. Min Act: -0.1700
Data Index: 349996 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5999. Min Range: -7.5999
Max Act: 6.7249. Min Act: -0.1700
Data Index: 2963089 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5999. Min Range: -7.5999
Max Act: 6.6624. Min Act: -0.1700
Data Index: 6143982 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5999. Min Range: -7.5999
Max Act: 6.6311. Min Act: -0.1700
Data Index: 7698122 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5999. Min Range: -7.5999
Max Act: 6.4749. Min Act: -0.1700
Data Index: 4676564 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5999. Min Range: -7.5999
Max Act: 6.4436. Min Act: -0.1700
Data Index: 6201482 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5999. Min Range: -7.5999
Max Act: 6.4124. Min Act: -0.1700
Data Index: 3624420 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5999. Min Range: -7.5999
Max Act: 6.4436. Min Act: -0.1700
Data Index: 821453 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5999. Min Range: -7.5999
Max Act: 6.4749. Min Act: -0.1700
Data Index: 7219505 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5999. Min Range: -7.5999
Max Act: 6.3186. Min Act: -0.1700
Data Index: 2871871 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5999. Min Range: -7.5999
Max Act: 6.2874. Min Act: -0.1700
Data Index: 5919793 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5999. Min Range: -7.5999
Max Act: 6.2874. Min Act: -0.1700
Data Index: 7568703 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5999. Min Range: -7.5999
Max Act: 6.3186. Min Act: -0.1700
Data Index: 1770097 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5999. Min Range: -7.5999
Max Act: 6.2874. Min Act: -0.1700
Data Index: 2963088 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5999. Min Range: -7.5999
Max Act: 6.2561. Min Act: -0.1700
Data Index: 2068529 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5999. Min Range: -7.5999
Max Act: 6.2561. Min Act: -0.1700
Data Index: 1922394 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5999. Min Range: -7.5999
Max Act: 6.2249. Min Act: -0.1700
Data Index: 4475580 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5999. Min Range: -7.5999
Max Act: 6.1936. Min Act: -0.1700
Data Index: 7698120 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5999. Min Range: -7.5999
Max Act: 6.1936. Min Act: -0.1700
Data Index: 6393609 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5999. Min Range: -7.5999
Max Act: 6.1936. Min Act: -0.1700
Data Index: 5143594 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19