Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 666 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6667. Min Range: -5.6667
Max Act: 5.6042. Min Act: -0.1700
Data Index: 3745925 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6667. Min Range: -5.6667
Max Act: 5.6667. Min Act: -0.1700
Data Index: 6467881 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6667. Min Range: -5.6667
Max Act: 5.6042. Min Act: -0.1700
Data Index: 8345988 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6667. Min Range: -5.6667
Max Act: 5.6042. Min Act: -0.1700
Data Index: 1905019 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6667. Min Range: -5.6667
Max Act: 5.6042. Min Act: -0.1700
Data Index: 683348 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6667. Min Range: -5.6667
Max Act: 5.5105. Min Act: -0.1700
Data Index: 6964075 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6667. Min Range: -5.6667
Max Act: 5.5105. Min Act: -0.1700
Data Index: 1575502 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6667. Min Range: -5.6667
Max Act: 5.4792. Min Act: -0.1700
Data Index: 6579358 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6667. Min Range: -5.6667
Max Act: 5.4792. Min Act: -0.1700
Data Index: 7286147 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6667. Min Range: -5.6667
Max Act: 5.4480. Min Act: -0.1700
Data Index: 6385600 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6667. Min Range: -5.6667
Max Act: 5.4167. Min Act: -0.1700
Data Index: 6963775 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6667. Min Range: -5.6667
Max Act: 5.4167. Min Act: -0.1700
Data Index: 4580754 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6667. Min Range: -5.6667
Max Act: 5.3855. Min Act: -0.1700
Data Index: 7738408 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6667. Min Range: -5.6667
Max Act: 5.4167. Min Act: -0.1700
Data Index: 7730145 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6667. Min Range: -5.6667
Max Act: 5.4167. Min Act: -0.1700
Data Index: 5270642 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6667. Min Range: -5.6667
Max Act: 5.3855. Min Act: -0.1700
Data Index: 624188 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6667. Min Range: -5.6667
Max Act: 5.3855. Min Act: -0.1700
Data Index: 2875096 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6667. Min Range: -5.6667
Max Act: 5.3855. Min Act: -0.1700
Data Index: 4953147 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6667. Min Range: -5.6667
Max Act: 5.3855. Min Act: -0.1700
Data Index: 6109427 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6667. Min Range: -5.6667
Max Act: 5.3542. Min Act: -0.1700
Data Index: 900143 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19