Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2156 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2480. Min Range: -5.2480
Max Act: 5.2480. Min Act: -0.1700
Data Index: 8785389 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2480. Min Range: -5.2480
Max Act: 5.1855. Min Act: -0.1700
Data Index: 7957820 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2480. Min Range: -5.2480
Max Act: 5.1543. Min Act: -0.1700
Data Index: 6701177 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2480. Min Range: -5.2480
Max Act: 5.0605. Min Act: -0.1700
Data Index: 1720078 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2480. Min Range: -5.2480
Max Act: 5.0293. Min Act: -0.1700
Data Index: 468456 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2480. Min Range: -5.2480
Max Act: 4.9980. Min Act: -0.1700
Data Index: 1321784 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2480. Min Range: -5.2480
Max Act: 4.9980. Min Act: -0.1700
Data Index: 514208 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2480. Min Range: -5.2480
Max Act: 4.9668. Min Act: -0.1700
Data Index: 5535951 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2480. Min Range: -5.2480
Max Act: 4.9355. Min Act: -0.1700
Data Index: 3052469 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2480. Min Range: -5.2480
Max Act: 4.9355. Min Act: -0.1700
Data Index: 1150613 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2480. Min Range: -5.2480
Max Act: 4.9043. Min Act: -0.1700
Data Index: 700013 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2480. Min Range: -5.2480
Max Act: 4.9043. Min Act: -0.1700
Data Index: 6786384 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2480. Min Range: -5.2480
Max Act: 4.8730. Min Act: -0.1700
Data Index: 522340 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2480. Min Range: -5.2480
Max Act: 4.9043. Min Act: -0.1700
Data Index: 902849 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2480. Min Range: -5.2480
Max Act: 4.9043. Min Act: -0.1700
Data Index: 4689400 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2480. Min Range: -5.2480
Max Act: 4.9043. Min Act: -0.1700
Data Index: 7839934 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2480. Min Range: -5.2480
Max Act: 4.8730. Min Act: -0.1700
Data Index: 8074142 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2480. Min Range: -5.2480
Max Act: 4.9043. Min Act: -0.1700
Data Index: 5667799 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2480. Min Range: -5.2480
Max Act: 4.8730. Min Act: -0.1700
Data Index: 7527632 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2480. Min Range: -5.2480
Max Act: 4.8418. Min Act: -0.1700
Data Index: 3693847 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19