Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3458 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9714. Min Range: -2.9714
Max Act: 2.9714. Min Act: -0.1700
Data Index: 2073080 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9714. Min Range: -2.9714
Max Act: 2.9397. Min Act: -0.1700
Data Index: 3610360 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9714. Min Range: -2.9714
Max Act: 2.9397. Min Act: -0.1700
Data Index: 6362518 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9714. Min Range: -2.9714
Max Act: 2.9239. Min Act: -0.1700
Data Index: 2922042 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9714. Min Range: -2.9714
Max Act: 2.8922. Min Act: -0.1700
Data Index: 3178268 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9714. Min Range: -2.9714
Max Act: 2.8763. Min Act: -0.1700
Data Index: 6333026 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9714. Min Range: -2.9714
Max Act: 2.8445. Min Act: -0.1700
Data Index: 4888289 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9714. Min Range: -2.9714
Max Act: 2.8604. Min Act: -0.1700
Data Index: 5427638 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9714. Min Range: -2.9714
Max Act: 2.8604. Min Act: -0.1700
Data Index: 8019026 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9714. Min Range: -2.9714
Max Act: 2.8604. Min Act: -0.1700
Data Index: 6601898 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9714. Min Range: -2.9714
Max Act: 2.8604. Min Act: -0.1700
Data Index: 6450386 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9714. Min Range: -2.9714
Max Act: 2.8445. Min Act: -0.1700
Data Index: 7515400 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9714. Min Range: -2.9714
Max Act: 2.8445. Min Act: -0.1700
Data Index: 3038598 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9714. Min Range: -2.9714
Max Act: 2.8445. Min Act: -0.1700
Data Index: 4530402 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9714. Min Range: -2.9714
Max Act: 2.8286. Min Act: -0.1700
Data Index: 5531197 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9714. Min Range: -2.9714
Max Act: 2.8445. Min Act: -0.1700
Data Index: 4475120 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9714. Min Range: -2.9714
Max Act: 2.8286. Min Act: -0.1700
Data Index: 3997491 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9714. Min Range: -2.9714
Max Act: 2.8127. Min Act: -0.1700
Data Index: 537139 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9714. Min Range: -2.9714
Max Act: 2.7968. Min Act: -0.1700
Data Index: 4615085 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9714. Min Range: -2.9714
Max Act: 2.8127. Min Act: -0.1700
Data Index: 811526 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19