Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5393 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9886. Min Range: -7.9886
Max Act: 7.9886. Min Act: -0.1700
Data Index: 4514914 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9886. Min Range: -7.9886
Max Act: 7.8636. Min Act: -0.1700
Data Index: 5376241 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9886. Min Range: -7.9886
Max Act: 7.8011. Min Act: -0.1700
Data Index: 6055120 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9886. Min Range: -7.9886
Max Act: 7.7074. Min Act: -0.1700
Data Index: 7870134 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9886. Min Range: -7.9886
Max Act: 7.6761. Min Act: -0.1700
Data Index: 3739416 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9886. Min Range: -7.9886
Max Act: 7.6761. Min Act: -0.1700
Data Index: 919431 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9886. Min Range: -7.9886
Max Act: 7.6136. Min Act: -0.1700
Data Index: 3327924 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9886. Min Range: -7.9886
Max Act: 7.5824. Min Act: -0.1700
Data Index: 7904885 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9886. Min Range: -7.9886
Max Act: 7.5824. Min Act: -0.1700
Data Index: 8251185 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9886. Min Range: -7.9886
Max Act: 7.5824. Min Act: -0.1700
Data Index: 7690920 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9886. Min Range: -7.9886
Max Act: 7.4886. Min Act: -0.1700
Data Index: 3254949 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9886. Min Range: -7.9886
Max Act: 7.4574. Min Act: -0.1700
Data Index: 5437991 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9886. Min Range: -7.9886
Max Act: 7.4574. Min Act: -0.1700
Data Index: 2120512 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9886. Min Range: -7.9886
Max Act: 7.3636. Min Act: -0.1700
Data Index: 91156 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9886. Min Range: -7.9886
Max Act: 7.3324. Min Act: -0.1700
Data Index: 5586569 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9886. Min Range: -7.9886
Max Act: 7.3011. Min Act: -0.1700
Data Index: 8409438 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9886. Min Range: -7.9886
Max Act: 7.2386. Min Act: -0.1700
Data Index: 5304303 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9886. Min Range: -7.9886
Max Act: 7.2699. Min Act: -0.1700
Data Index: 732233 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9886. Min Range: -7.9886
Max Act: 7.2699. Min Act: -0.1700
Data Index: 4174693 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9886. Min Range: -7.9886
Max Act: 7.2386. Min Act: -0.1700
Data Index: 7953718 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19