Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 203 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1900. Min Range: -6.1900
Max Act: 6.1588. Min Act: -0.1700
Data Index: 7942743 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1900. Min Range: -6.1900
Max Act: 6.0963. Min Act: -0.1700
Data Index: 1377559 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1900. Min Range: -6.1900
Max Act: 6.1900. Min Act: -0.1700
Data Index: 8407496 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1900. Min Range: -6.1900
Max Act: 5.9400. Min Act: -0.1700
Data Index: 7435957 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1900. Min Range: -6.1900
Max Act: 5.7213. Min Act: -0.1700
Data Index: 6065118 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1900. Min Range: -6.1900
Max Act: 5.6900. Min Act: -0.1700
Data Index: 4987306 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1900. Min Range: -6.1900
Max Act: 5.6588. Min Act: -0.1700
Data Index: 5242814 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1900. Min Range: -6.1900
Max Act: 5.6275. Min Act: -0.1700
Data Index: 8704229 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1900. Min Range: -6.1900
Max Act: 5.5963. Min Act: -0.1700
Data Index: 5829084 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1900. Min Range: -6.1900
Max Act: 5.6275. Min Act: -0.1700
Data Index: 7287861 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1900. Min Range: -6.1900
Max Act: 5.5963. Min Act: -0.1700
Data Index: 8321221 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1900. Min Range: -6.1900
Max Act: 5.5963. Min Act: -0.1700
Data Index: 6260875 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1900. Min Range: -6.1900
Max Act: 5.5650. Min Act: -0.1700
Data Index: 7910592 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1900. Min Range: -6.1900
Max Act: 5.5650. Min Act: -0.1700
Data Index: 2093506 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1900. Min Range: -6.1900
Max Act: 5.5650. Min Act: -0.1700
Data Index: 8726323 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1900. Min Range: -6.1900
Max Act: 5.5650. Min Act: -0.1700
Data Index: 2009860 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1900. Min Range: -6.1900
Max Act: 5.5025. Min Act: -0.1700
Data Index: 7464976 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1900. Min Range: -6.1900
Max Act: 5.5025. Min Act: -0.1700
Data Index: 7266964 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1900. Min Range: -6.1900
Max Act: 5.4713. Min Act: -0.1700
Data Index: 1265147 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1900. Min Range: -6.1900
Max Act: 5.4400. Min Act: -0.1700
Data Index: 2580766 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19