Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4770 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2776. Min Range: -7.2776
Max Act: 7.2776. Min Act: -0.1700
Data Index: 3538983 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2776. Min Range: -7.2776
Max Act: 7.2464. Min Act: -0.1700
Data Index: 3423895 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2776. Min Range: -7.2776
Max Act: 7.1214. Min Act: -0.1700
Data Index: 5063584 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2776. Min Range: -7.2776
Max Act: 7.1526. Min Act: -0.1700
Data Index: 1905257 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2776. Min Range: -7.2776
Max Act: 7.0901. Min Act: -0.1700
Data Index: 3423887 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2776. Min Range: -7.2776
Max Act: 7.0276. Min Act: -0.1700
Data Index: 8058265 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2776. Min Range: -7.2776
Max Act: 7.0276. Min Act: -0.1700
Data Index: 6334059 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2776. Min Range: -7.2776
Max Act: 7.0276. Min Act: -0.1700
Data Index: 49751 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2776. Min Range: -7.2776
Max Act: 6.9964. Min Act: -0.1700
Data Index: 7699569 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2776. Min Range: -7.2776
Max Act: 6.9339. Min Act: -0.1700
Data Index: 3308941 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2776. Min Range: -7.2776
Max Act: 6.9651. Min Act: -0.1700
Data Index: 2196627 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2776. Min Range: -7.2776
Max Act: 6.9339. Min Act: -0.1700
Data Index: 5754809 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2776. Min Range: -7.2776
Max Act: 6.9026. Min Act: -0.1700
Data Index: 2212904 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2776. Min Range: -7.2776
Max Act: 6.8714. Min Act: -0.1700
Data Index: 1307087 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2776. Min Range: -7.2776
Max Act: 6.8714. Min Act: -0.1700
Data Index: 8580904 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2776. Min Range: -7.2776
Max Act: 6.8714. Min Act: -0.1700
Data Index: 7998897 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2776. Min Range: -7.2776
Max Act: 6.8714. Min Act: -0.1700
Data Index: 3180338 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2776. Min Range: -7.2776
Max Act: 6.8714. Min Act: -0.1700
Data Index: 2171921 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2776. Min Range: -7.2776
Max Act: 6.8401. Min Act: -0.1700
Data Index: 6215341 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2776. Min Range: -7.2776
Max Act: 6.8089. Min Act: -0.1700
Data Index: 4606820 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19