Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4217 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7077. Min Range: -5.7077
Max Act: 5.7077. Min Act: -0.1700
Data Index: 2695205 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7077. Min Range: -5.7077
Max Act: 5.6452. Min Act: -0.1700
Data Index: 7728553 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7077. Min Range: -5.7077
Max Act: 5.5514. Min Act: -0.1700
Data Index: 5140267 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7077. Min Range: -5.7077
Max Act: 5.5514. Min Act: -0.1700
Data Index: 227531 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7077. Min Range: -5.7077
Max Act: 5.5202. Min Act: -0.1700
Data Index: 1532823 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7077. Min Range: -5.7077
Max Act: 5.4889. Min Act: -0.1700
Data Index: 8614098 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7077. Min Range: -5.7077
Max Act: 5.4889. Min Act: -0.1700
Data Index: 5115746 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7077. Min Range: -5.7077
Max Act: 5.4889. Min Act: -0.1700
Data Index: 4072736 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7077. Min Range: -5.7077
Max Act: 5.4264. Min Act: -0.1700
Data Index: 7116767 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7077. Min Range: -5.7077
Max Act: 5.4264. Min Act: -0.1700
Data Index: 1837914 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7077. Min Range: -5.7077
Max Act: 5.3952. Min Act: -0.1700
Data Index: 6164988 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7077. Min Range: -5.7077
Max Act: 5.3952. Min Act: -0.1700
Data Index: 1398521 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7077. Min Range: -5.7077
Max Act: 5.3952. Min Act: -0.1700
Data Index: 871353 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7077. Min Range: -5.7077
Max Act: 5.3639. Min Act: -0.1700
Data Index: 842053 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7077. Min Range: -5.7077
Max Act: 5.3639. Min Act: -0.1700
Data Index: 565949 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7077. Min Range: -5.7077
Max Act: 5.3639. Min Act: -0.1700
Data Index: 2481053 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7077. Min Range: -5.7077
Max Act: 5.3639. Min Act: -0.1700
Data Index: 7897814 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7077. Min Range: -5.7077
Max Act: 5.3327. Min Act: -0.1700
Data Index: 248275 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7077. Min Range: -5.7077
Max Act: 5.3327. Min Act: -0.1700
Data Index: 2679233 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7077. Min Range: -5.7077
Max Act: 5.3327. Min Act: -0.1700
Data Index: 5255385 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19