Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4820 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8002. Min Range: -7.8002
Max Act: 7.8002. Min Act: -0.1700
Data Index: 3168215 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8002. Min Range: -7.8002
Max Act: 7.7690. Min Act: -0.1700
Data Index: 7548367 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8002. Min Range: -7.8002
Max Act: 7.7690. Min Act: -0.1700
Data Index: 8225810 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8002. Min Range: -7.8002
Max Act: 7.6127. Min Act: -0.1700
Data Index: 2428416 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8002. Min Range: -7.8002
Max Act: 7.5502. Min Act: -0.1700
Data Index: 1324594 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8002. Min Range: -7.8002
Max Act: 7.3940. Min Act: -0.1700
Data Index: 4483965 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8002. Min Range: -7.8002
Max Act: 7.3002. Min Act: -0.1700
Data Index: 5088789 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8002. Min Range: -7.8002
Max Act: 7.3315. Min Act: -0.1700
Data Index: 7181324 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8002. Min Range: -7.8002
Max Act: 7.2690. Min Act: -0.1700
Data Index: 4244779 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8002. Min Range: -7.8002
Max Act: 7.2690. Min Act: -0.1700
Data Index: 4782938 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8002. Min Range: -7.8002
Max Act: 7.2377. Min Act: -0.1700
Data Index: 5729266 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8002. Min Range: -7.8002
Max Act: 7.2377. Min Act: -0.1700
Data Index: 4313932 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8002. Min Range: -7.8002
Max Act: 7.2377. Min Act: -0.1700
Data Index: 5534844 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8002. Min Range: -7.8002
Max Act: 7.2377. Min Act: -0.1700
Data Index: 1820293 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8002. Min Range: -7.8002
Max Act: 7.2065. Min Act: -0.1700
Data Index: 1324590 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8002. Min Range: -7.8002
Max Act: 7.1752. Min Act: -0.1700
Data Index: 6593444 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8002. Min Range: -7.8002
Max Act: 7.1440. Min Act: -0.1700
Data Index: 3520679 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8002. Min Range: -7.8002
Max Act: 7.1752. Min Act: -0.1700
Data Index: 2428415 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8002. Min Range: -7.8002
Max Act: 7.1440. Min Act: -0.1700
Data Index: 1324598 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8002. Min Range: -7.8002
Max Act: 7.1127. Min Act: -0.1700
Data Index: 1324589 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19