Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2139 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0134. Min Range: -8.0134
Max Act: 8.0134. Min Act: -0.1700
Data Index: 1131802 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0134. Min Range: -8.0134
Max Act: 7.8884. Min Act: -0.1700
Data Index: 7250084 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0134. Min Range: -8.0134
Max Act: 7.8884. Min Act: -0.1700
Data Index: 7250086 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0134. Min Range: -8.0134
Max Act: 7.8884. Min Act: -0.1700
Data Index: 7227802 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0134. Min Range: -8.0134
Max Act: 7.8884. Min Act: -0.1700
Data Index: 6434589 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0134. Min Range: -8.0134
Max Act: 7.7634. Min Act: -0.1700
Data Index: 3069351 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0134. Min Range: -8.0134
Max Act: 7.7634. Min Act: -0.1700
Data Index: 378061 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0134. Min Range: -8.0134
Max Act: 7.7009. Min Act: -0.1700
Data Index: 1327183 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0134. Min Range: -8.0134
Max Act: 7.7009. Min Act: -0.1700
Data Index: 290399 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0134. Min Range: -8.0134
Max Act: 7.7009. Min Act: -0.1700
Data Index: 2670710 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0134. Min Range: -8.0134
Max Act: 7.6384. Min Act: -0.1700
Data Index: 7161142 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0134. Min Range: -8.0134
Max Act: 7.6696. Min Act: -0.1700
Data Index: 3865415 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0134. Min Range: -8.0134
Max Act: 7.6384. Min Act: -0.1700
Data Index: 4868260 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0134. Min Range: -8.0134
Max Act: 7.6384. Min Act: -0.1700
Data Index: 7618049 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0134. Min Range: -8.0134
Max Act: 7.5446. Min Act: -0.1700
Data Index: 7250083 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0134. Min Range: -8.0134
Max Act: 7.5759. Min Act: -0.1700
Data Index: 2967974 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0134. Min Range: -8.0134
Max Act: 7.5759. Min Act: -0.1700
Data Index: 3449589 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0134. Min Range: -8.0134
Max Act: 7.5446. Min Act: -0.1700
Data Index: 3984470 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0134. Min Range: -8.0134
Max Act: 7.5446. Min Act: -0.1700
Data Index: 1480643 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0134. Min Range: -8.0134
Max Act: 7.5446. Min Act: -0.1700
Data Index: 6525024 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19