Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2914 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1676. Min Range: -7.1676
Max Act: 7.1676. Min Act: -0.1700
Data Index: 3750879 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1676. Min Range: -7.1676
Max Act: 7.1051. Min Act: -0.1700
Data Index: 5403970 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1676. Min Range: -7.1676
Max Act: 7.1051. Min Act: -0.1700
Data Index: 6848242 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1676. Min Range: -7.1676
Max Act: 6.9801. Min Act: -0.1700
Data Index: 728808 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1676. Min Range: -7.1676
Max Act: 6.9489. Min Act: -0.1700
Data Index: 63543 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1676. Min Range: -7.1676
Max Act: 6.9489. Min Act: -0.1700
Data Index: 1716097 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1676. Min Range: -7.1676
Max Act: 6.9176. Min Act: -0.1700
Data Index: 3624336 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1676. Min Range: -7.1676
Max Act: 6.8864. Min Act: -0.1700
Data Index: 7805822 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1676. Min Range: -7.1676
Max Act: 6.8864. Min Act: -0.1700
Data Index: 7029736 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1676. Min Range: -7.1676
Max Act: 6.8551. Min Act: -0.1700
Data Index: 8497811 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1676. Min Range: -7.1676
Max Act: 6.8551. Min Act: -0.1700
Data Index: 2459601 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1676. Min Range: -7.1676
Max Act: 6.8551. Min Act: -0.1700
Data Index: 7276908 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1676. Min Range: -7.1676
Max Act: 6.8239. Min Act: -0.1700
Data Index: 6893625 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1676. Min Range: -7.1676
Max Act: 6.8239. Min Act: -0.1700
Data Index: 3234103 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1676. Min Range: -7.1676
Max Act: 6.7926. Min Act: -0.1700
Data Index: 3611755 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1676. Min Range: -7.1676
Max Act: 6.7926. Min Act: -0.1700
Data Index: 7958938 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1676. Min Range: -7.1676
Max Act: 6.7614. Min Act: -0.1700
Data Index: 1349320 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1676. Min Range: -7.1676
Max Act: 6.7926. Min Act: -0.1700
Data Index: 3688648 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1676. Min Range: -7.1676
Max Act: 6.7614. Min Act: -0.1700
Data Index: 1201641 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1676. Min Range: -7.1676
Max Act: 6.7926. Min Act: -0.1700
Data Index: 5911465 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19