Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3384 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7077. Min Range: -6.7077
Max Act: 6.7077. Min Act: -0.1700
Data Index: 871112 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7077. Min Range: -6.7077
Max Act: 6.6765. Min Act: -0.1700
Data Index: 4512248 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7077. Min Range: -6.7077
Max Act: 6.5202. Min Act: -0.1700
Data Index: 8175099 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7077. Min Range: -6.7077
Max Act: 6.5202. Min Act: -0.1700
Data Index: 1221601 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7077. Min Range: -6.7077
Max Act: 6.5515. Min Act: -0.1700
Data Index: 994574 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7077. Min Range: -6.7077
Max Act: 6.4890. Min Act: -0.1700
Data Index: 8428966 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7077. Min Range: -6.7077
Max Act: 6.5202. Min Act: -0.1700
Data Index: 8049211 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7077. Min Range: -6.7077
Max Act: 6.4577. Min Act: -0.1700
Data Index: 8489773 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7077. Min Range: -6.7077
Max Act: 6.4577. Min Act: -0.1700
Data Index: 5773619 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7077. Min Range: -6.7077
Max Act: 6.4577. Min Act: -0.1700
Data Index: 3705841 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7077. Min Range: -6.7077
Max Act: 6.4265. Min Act: -0.1700
Data Index: 8117097 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7077. Min Range: -6.7077
Max Act: 6.4265. Min Act: -0.1700
Data Index: 5578738 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7077. Min Range: -6.7077
Max Act: 6.3952. Min Act: -0.1700
Data Index: 7161559 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7077. Min Range: -6.7077
Max Act: 6.3640. Min Act: -0.1700
Data Index: 8627093 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7077. Min Range: -6.7077
Max Act: 6.3640. Min Act: -0.1700
Data Index: 4755058 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7077. Min Range: -6.7077
Max Act: 6.3640. Min Act: -0.1700
Data Index: 1739702 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7077. Min Range: -6.7077
Max Act: 6.3327. Min Act: -0.1700
Data Index: 6355122 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7077. Min Range: -6.7077
Max Act: 6.3327. Min Act: -0.1700
Data Index: 3691598 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7077. Min Range: -6.7077
Max Act: 6.3015. Min Act: -0.1700
Data Index: 2551162 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7077. Min Range: -6.7077
Max Act: 6.3015. Min Act: -0.1700
Data Index: 732298 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19