Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4437 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8155. Min Range: -6.8155
Max Act: 6.8155. Min Act: -0.1700
Data Index: 6631415 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8155. Min Range: -6.8155
Max Act: 6.8155. Min Act: -0.1700
Data Index: 6406782 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8155. Min Range: -6.8155
Max Act: 6.7842. Min Act: -0.1700
Data Index: 5533343 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8155. Min Range: -6.8155
Max Act: 6.5655. Min Act: -0.1700
Data Index: 2427358 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8155. Min Range: -6.8155
Max Act: 6.5030. Min Act: -0.1700
Data Index: 8199975 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8155. Min Range: -6.8155
Max Act: 6.4717. Min Act: -0.1700
Data Index: 8681702 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8155. Min Range: -6.8155
Max Act: 6.4092. Min Act: -0.1700
Data Index: 3903353 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8155. Min Range: -6.8155
Max Act: 6.4092. Min Act: -0.1700
Data Index: 6844594 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8155. Min Range: -6.8155
Max Act: 6.3780. Min Act: -0.1700
Data Index: 4225560 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8155. Min Range: -6.8155
Max Act: 6.3467. Min Act: -0.1700
Data Index: 1658573 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8155. Min Range: -6.8155
Max Act: 6.3780. Min Act: -0.1700
Data Index: 5446633 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8155. Min Range: -6.8155
Max Act: 6.3155. Min Act: -0.1700
Data Index: 6259163 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8155. Min Range: -6.8155
Max Act: 6.3155. Min Act: -0.1700
Data Index: 6845548 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8155. Min Range: -6.8155
Max Act: 6.3155. Min Act: -0.1700
Data Index: 5583118 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8155. Min Range: -6.8155
Max Act: 6.2842. Min Act: -0.1700
Data Index: 6949946 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8155. Min Range: -6.8155
Max Act: 6.2530. Min Act: -0.1700
Data Index: 5393773 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8155. Min Range: -6.8155
Max Act: 6.2530. Min Act: -0.1700
Data Index: 812302 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8155. Min Range: -6.8155
Max Act: 6.2530. Min Act: -0.1700
Data Index: 4239617 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8155. Min Range: -6.8155
Max Act: 6.2217. Min Act: -0.1700
Data Index: 7917394 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8155. Min Range: -6.8155
Max Act: 6.2217. Min Act: -0.1700
Data Index: 6539119 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19