Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4010 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0288. Min Range: -6.0288
Max Act: 6.0288. Min Act: -0.1700
Data Index: 7241352 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0288. Min Range: -6.0288
Max Act: 5.9038. Min Act: -0.1700
Data Index: 8219944 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0288. Min Range: -6.0288
Max Act: 5.8725. Min Act: -0.1700
Data Index: 8267721 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0288. Min Range: -6.0288
Max Act: 5.7475. Min Act: -0.1700
Data Index: 1181590 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0288. Min Range: -6.0288
Max Act: 5.7163. Min Act: -0.1700
Data Index: 5972811 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0288. Min Range: -6.0288
Max Act: 5.6225. Min Act: -0.1700
Data Index: 4800724 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0288. Min Range: -6.0288
Max Act: 5.6538. Min Act: -0.1700
Data Index: 6412126 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0288. Min Range: -6.0288
Max Act: 5.6225. Min Act: -0.1700
Data Index: 5682425 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0288. Min Range: -6.0288
Max Act: 5.5913. Min Act: -0.1700
Data Index: 592738 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0288. Min Range: -6.0288
Max Act: 5.5288. Min Act: -0.1700
Data Index: 4208191 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0288. Min Range: -6.0288
Max Act: 5.4975. Min Act: -0.1700
Data Index: 8618796 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0288. Min Range: -6.0288
Max Act: 5.4975. Min Act: -0.1700
Data Index: 749035 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0288. Min Range: -6.0288
Max Act: 5.4975. Min Act: -0.1700
Data Index: 2783505 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0288. Min Range: -6.0288
Max Act: 5.4350. Min Act: -0.1700
Data Index: 3091256 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0288. Min Range: -6.0288
Max Act: 5.4350. Min Act: -0.1700
Data Index: 6087672 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0288. Min Range: -6.0288
Max Act: 5.3725. Min Act: -0.1700
Data Index: 3703521 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0288. Min Range: -6.0288
Max Act: 5.4038. Min Act: -0.1700
Data Index: 8608547 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0288. Min Range: -6.0288
Max Act: 5.3725. Min Act: -0.1700
Data Index: 1805317 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0288. Min Range: -6.0288
Max Act: 5.3725. Min Act: -0.1700
Data Index: 2345265 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0288. Min Range: -6.0288
Max Act: 5.3725. Min Act: -0.1700
Data Index: 7274420 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19