Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4646 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1190. Min Range: -5.1190
Max Act: 5.1190. Min Act: -0.1700
Data Index: 2571867 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1190. Min Range: -5.1190
Max Act: 5.0565. Min Act: -0.1700
Data Index: 3528623 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1190. Min Range: -5.1190
Max Act: 5.0565. Min Act: -0.1700
Data Index: 5772919 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1190. Min Range: -5.1190
Max Act: 5.0253. Min Act: -0.1700
Data Index: 7104410 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1190. Min Range: -5.1190
Max Act: 4.9628. Min Act: -0.1700
Data Index: 6703760 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1190. Min Range: -5.1190
Max Act: 4.9315. Min Act: -0.1700
Data Index: 8397085 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1190. Min Range: -5.1190
Max Act: 4.9003. Min Act: -0.1700
Data Index: 646751 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1190. Min Range: -5.1190
Max Act: 4.9003. Min Act: -0.1700
Data Index: 3470386 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1190. Min Range: -5.1190
Max Act: 4.9003. Min Act: -0.1700
Data Index: 5121715 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1190. Min Range: -5.1190
Max Act: 4.9003. Min Act: -0.1700
Data Index: 2850680 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1190. Min Range: -5.1190
Max Act: 4.9003. Min Act: -0.1700
Data Index: 5168568 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1190. Min Range: -5.1190
Max Act: 4.9003. Min Act: -0.1700
Data Index: 1970072 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1190. Min Range: -5.1190
Max Act: 4.8690. Min Act: -0.1700
Data Index: 8542698 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1190. Min Range: -5.1190
Max Act: 4.8690. Min Act: -0.1700
Data Index: 7331982 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1190. Min Range: -5.1190
Max Act: 4.8690. Min Act: -0.1700
Data Index: 7708993 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1190. Min Range: -5.1190
Max Act: 4.8378. Min Act: -0.1700
Data Index: 646612 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1190. Min Range: -5.1190
Max Act: 4.8690. Min Act: -0.1700
Data Index: 8002672 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1190. Min Range: -5.1190
Max Act: 4.8378. Min Act: -0.1700
Data Index: 4144728 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1190. Min Range: -5.1190
Max Act: 4.8378. Min Act: -0.1700
Data Index: 73067 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1190. Min Range: -5.1190
Max Act: 4.8065. Min Act: -0.1700
Data Index: 7371105 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #19