Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 970 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6143. Min Range: -5.6143
Max Act: 5.6143. Min Act: -0.1700
Data Index: 5295687 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6143. Min Range: -5.6143
Max Act: 5.4268. Min Act: -0.1700
Data Index: 370910 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6143. Min Range: -5.6143
Max Act: 5.4268. Min Act: -0.1700
Data Index: 7013035 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6143. Min Range: -5.6143
Max Act: 5.3955. Min Act: -0.1700
Data Index: 5086668 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6143. Min Range: -5.6143
Max Act: 5.3955. Min Act: -0.1700
Data Index: 4313819 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6143. Min Range: -5.6143
Max Act: 5.3643. Min Act: -0.1700
Data Index: 1269620 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6143. Min Range: -5.6143
Max Act: 5.3330. Min Act: -0.1700
Data Index: 6785774 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6143. Min Range: -5.6143
Max Act: 5.3330. Min Act: -0.1700
Data Index: 8418674 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6143. Min Range: -5.6143
Max Act: 5.3330. Min Act: -0.1700
Data Index: 139863 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6143. Min Range: -5.6143
Max Act: 5.3330. Min Act: -0.1700
Data Index: 4489122 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6143. Min Range: -5.6143
Max Act: 5.3330. Min Act: -0.1700
Data Index: 3977183 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6143. Min Range: -5.6143
Max Act: 5.2705. Min Act: -0.1700
Data Index: 2498895 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6143. Min Range: -5.6143
Max Act: 5.2705. Min Act: -0.1700
Data Index: 3303148 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6143. Min Range: -5.6143
Max Act: 5.2705. Min Act: -0.1700
Data Index: 6979664 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6143. Min Range: -5.6143
Max Act: 5.2705. Min Act: -0.1700
Data Index: 587031 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6143. Min Range: -5.6143
Max Act: 5.2393. Min Act: -0.1700
Data Index: 5428583 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6143. Min Range: -5.6143
Max Act: 5.2705. Min Act: -0.1700
Data Index: 2937006 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6143. Min Range: -5.6143
Max Act: 5.2393. Min Act: -0.1700
Data Index: 2833272 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6143. Min Range: -5.6143
Max Act: 5.2393. Min Act: -0.1700
Data Index: 3647396 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6143. Min Range: -5.6143
Max Act: 5.2393. Min Act: -0.1700
Data Index: 386944 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19