Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3896 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4589. Min Range: -5.4589
Max Act: 5.4589. Min Act: -0.1700
Data Index: 5507538 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4589. Min Range: -5.4589
Max Act: 5.4589. Min Act: -0.1700
Data Index: 3016735 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4589. Min Range: -5.4589
Max Act: 5.4277. Min Act: -0.1700
Data Index: 3335425 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4589. Min Range: -5.4589
Max Act: 5.4277. Min Act: -0.1700
Data Index: 4646043 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4589. Min Range: -5.4589
Max Act: 5.3964. Min Act: -0.1700
Data Index: 5937956 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4589. Min Range: -5.4589
Max Act: 5.3964. Min Act: -0.1700
Data Index: 4886567 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4589. Min Range: -5.4589
Max Act: 5.3964. Min Act: -0.1700
Data Index: 8734476 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4589. Min Range: -5.4589
Max Act: 5.3964. Min Act: -0.1700
Data Index: 8161639 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4589. Min Range: -5.4589
Max Act: 5.3964. Min Act: -0.1700
Data Index: 7960363 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4589. Min Range: -5.4589
Max Act: 5.3964. Min Act: -0.1700
Data Index: 7882842 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4589. Min Range: -5.4589
Max Act: 5.3652. Min Act: -0.1700
Data Index: 7857952 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4589. Min Range: -5.4589
Max Act: 5.3964. Min Act: -0.1700
Data Index: 7338231 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4589. Min Range: -5.4589
Max Act: 5.3964. Min Act: -0.1700
Data Index: 231942 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4589. Min Range: -5.4589
Max Act: 5.3964. Min Act: -0.1700
Data Index: 1230321 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4589. Min Range: -5.4589
Max Act: 5.3964. Min Act: -0.1700
Data Index: 6366648 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4589. Min Range: -5.4589
Max Act: 5.3652. Min Act: -0.1700
Data Index: 2884582 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4589. Min Range: -5.4589
Max Act: 5.3652. Min Act: -0.1700
Data Index: 4873690 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4589. Min Range: -5.4589
Max Act: 5.3652. Min Act: -0.1700
Data Index: 5185625 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4589. Min Range: -5.4589
Max Act: 5.3652. Min Act: -0.1700
Data Index: 162077 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4589. Min Range: -5.4589
Max Act: 5.3652. Min Act: -0.1700
Data Index: 5567564 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19