Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2242 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8864. Min Range: -3.8864
Max Act: 3.8864. Min Act: -0.1700
Data Index: 6736182 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8864. Min Range: -3.8864
Max Act: 3.3228. Min Act: -0.1700
Data Index: 1474306 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8864. Min Range: -3.8864
Max Act: 3.2443. Min Act: -0.1700
Data Index: 8433544 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8864. Min Range: -3.8864
Max Act: 3.2286. Min Act: -0.1700
Data Index: 883799 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8864. Min Range: -3.8864
Max Act: 3.2129. Min Act: -0.1700
Data Index: 2972671 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8864. Min Range: -3.8864
Max Act: 3.1657. Min Act: -0.1700
Data Index: 6342911 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8864. Min Range: -3.8864
Max Act: 3.1342. Min Act: -0.1700
Data Index: 5941937 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8864. Min Range: -3.8864
Max Act: 3.0869. Min Act: -0.1700
Data Index: 2285888 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8864. Min Range: -3.8864
Max Act: 3.1027. Min Act: -0.1700
Data Index: 7819455 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8864. Min Range: -3.8864
Max Act: 3.0396. Min Act: -0.1700
Data Index: 6942153 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8864. Min Range: -3.8864
Max Act: 3.0554. Min Act: -0.1700
Data Index: 8130714 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8864. Min Range: -3.8864
Max Act: 3.0396. Min Act: -0.1700
Data Index: 857415 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8864. Min Range: -3.8864
Max Act: 3.0080. Min Act: -0.1700
Data Index: 1625840 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8864. Min Range: -3.8864
Max Act: 3.0080. Min Act: -0.1700
Data Index: 3612250 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8864. Min Range: -3.8864
Max Act: 2.9922. Min Act: -0.1700
Data Index: 6686620 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8864. Min Range: -3.8864
Max Act: 2.9922. Min Act: -0.1700
Data Index: 6267713 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8864. Min Range: -3.8864
Max Act: 2.9922. Min Act: -0.1700
Data Index: 2570331 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8864. Min Range: -3.8864
Max Act: 2.9764. Min Act: -0.1700
Data Index: 3179847 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8864. Min Range: -3.8864
Max Act: 2.9922. Min Act: -0.1700
Data Index: 539908 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8864. Min Range: -3.8864
Max Act: 2.9922. Min Act: -0.1700
Data Index: 4664090 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19