Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3378 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6965. Min Range: -2.6965
Max Act: 2.6965. Min Act: -0.1700
Data Index: 5577604 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6965. Min Range: -2.6965
Max Act: 2.6645. Min Act: -0.1700
Data Index: 6638375 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6965. Min Range: -2.6965
Max Act: 2.6485. Min Act: -0.1699
Data Index: 1018555 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6965. Min Range: -2.6965
Max Act: 2.6485. Min Act: -0.1700
Data Index: 7151254 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6965. Min Range: -2.6965
Max Act: 2.6485. Min Act: -0.1700
Data Index: 235760 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6965. Min Range: -2.6965
Max Act: 2.6485. Min Act: -0.1700
Data Index: 955556 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6965. Min Range: -2.6965
Max Act: 2.6485. Min Act: -0.1700
Data Index: 6204890 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6965. Min Range: -2.6965
Max Act: 2.6324. Min Act: -0.1700
Data Index: 8774229 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6965. Min Range: -2.6965
Max Act: 2.6324. Min Act: -0.1700
Data Index: 1202240 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6965. Min Range: -2.6965
Max Act: 2.6324. Min Act: -0.1700
Data Index: 7169896 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6965. Min Range: -2.6965
Max Act: 2.6002. Min Act: -0.1700
Data Index: 7106231 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6965. Min Range: -2.6965
Max Act: 2.6002. Min Act: -0.1700
Data Index: 7936112 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6965. Min Range: -2.6965
Max Act: 2.5841. Min Act: -0.1700
Data Index: 2857410 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6965. Min Range: -2.6965
Max Act: 2.6163. Min Act: -0.1700
Data Index: 2047607 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6965. Min Range: -2.6965
Max Act: 2.6002. Min Act: -0.1700
Data Index: 7355468 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6965. Min Range: -2.6965
Max Act: 2.6002. Min Act: -0.1700
Data Index: 5815869 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6965. Min Range: -2.6965
Max Act: 2.6002. Min Act: -0.1700
Data Index: 7169894 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6965. Min Range: -2.6965
Max Act: 2.5841. Min Act: -0.1700
Data Index: 3712789 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6965. Min Range: -2.6965
Max Act: 2.5841. Min Act: -0.1700
Data Index: 161802 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6965. Min Range: -2.6965
Max Act: 2.5841. Min Act: -0.1700
Data Index: 548623 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19