Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2441 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1119. Min Range: -9.1119
Max Act: 9.1119. Min Act: -0.1700
Data Index: 3033763 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1119. Min Range: -9.1119
Max Act: 9.0494. Min Act: -0.1700
Data Index: 3565413 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1119. Min Range: -9.1119
Max Act: 8.9244. Min Act: -0.1700
Data Index: 5788998 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1119. Min Range: -9.1119
Max Act: 8.9244. Min Act: -0.1700
Data Index: 729911 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1119. Min Range: -9.1119
Max Act: 8.7994. Min Act: -0.1700
Data Index: 2709858 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1119. Min Range: -9.1119
Max Act: 8.8619. Min Act: -0.1700
Data Index: 2569182 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1119. Min Range: -9.1119
Max Act: 8.8619. Min Act: -0.1700
Data Index: 463053 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1119. Min Range: -9.1119
Max Act: 8.7994. Min Act: -0.1700
Data Index: 3460056 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1119. Min Range: -9.1119
Max Act: 8.6744. Min Act: -0.1700
Data Index: 7539293 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1119. Min Range: -9.1119
Max Act: 8.7369. Min Act: -0.1700
Data Index: 6635073 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1119. Min Range: -9.1119
Max Act: 8.7369. Min Act: -0.1700
Data Index: 3067275 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1119. Min Range: -9.1119
Max Act: 8.7369. Min Act: -0.1700
Data Index: 8634107 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1119. Min Range: -9.1119
Max Act: 8.6744. Min Act: -0.1700
Data Index: 2162041 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1119. Min Range: -9.1119
Max Act: 8.6744. Min Act: -0.1700
Data Index: 8798475 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1119. Min Range: -9.1119
Max Act: 8.6744. Min Act: -0.1700
Data Index: 8154699 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1119. Min Range: -9.1119
Max Act: 8.6119. Min Act: -0.1700
Data Index: 5919186 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1119. Min Range: -9.1119
Max Act: 8.6119. Min Act: -0.1700
Data Index: 5919533 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1119. Min Range: -9.1119
Max Act: 8.6119. Min Act: -0.1700
Data Index: 3531914 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1119. Min Range: -9.1119
Max Act: 8.5494. Min Act: -0.1700
Data Index: 3456715 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1119. Min Range: -9.1119
Max Act: 8.5494. Min Act: -0.1700
Data Index: 665327 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19