Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2943 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1543. Min Range: -5.1543
Max Act: 5.1543. Min Act: -0.1700
Data Index: 4985436 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1543. Min Range: -5.1543
Max Act: 5.0918. Min Act: -0.1700
Data Index: 3749120 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1543. Min Range: -5.1543
Max Act: 5.0918. Min Act: -0.1700
Data Index: 4632765 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1543. Min Range: -5.1543
Max Act: 5.0606. Min Act: -0.1700
Data Index: 4593031 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1543. Min Range: -5.1543
Max Act: 5.0293. Min Act: -0.1700
Data Index: 694974 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1543. Min Range: -5.1543
Max Act: 4.9981. Min Act: -0.1700
Data Index: 37682 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1543. Min Range: -5.1543
Max Act: 5.0293. Min Act: -0.1700
Data Index: 3566441 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1543. Min Range: -5.1543
Max Act: 4.9668. Min Act: -0.1700
Data Index: 4515540 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1543. Min Range: -5.1543
Max Act: 4.9981. Min Act: -0.1700
Data Index: 646262 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1543. Min Range: -5.1543
Max Act: 4.9356. Min Act: -0.1700
Data Index: 1667293 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1543. Min Range: -5.1543
Max Act: 4.9356. Min Act: -0.1700
Data Index: 6640171 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1543. Min Range: -5.1543
Max Act: 4.9043. Min Act: -0.1700
Data Index: 5848730 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1543. Min Range: -5.1543
Max Act: 4.9356. Min Act: -0.1700
Data Index: 1000177 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1543. Min Range: -5.1543
Max Act: 4.9043. Min Act: -0.1700
Data Index: 7798781 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1543. Min Range: -5.1543
Max Act: 4.8731. Min Act: -0.1700
Data Index: 4892827 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1543. Min Range: -5.1543
Max Act: 4.8418. Min Act: -0.1700
Data Index: 7632735 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1543. Min Range: -5.1543
Max Act: 4.8418. Min Act: -0.1700
Data Index: 4528797 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1543. Min Range: -5.1543
Max Act: 4.8418. Min Act: -0.1700
Data Index: 5854780 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1543. Min Range: -5.1543
Max Act: 4.8418. Min Act: -0.1700
Data Index: 4700921 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1543. Min Range: -5.1543
Max Act: 4.8418. Min Act: -0.1700
Data Index: 900996 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19