Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1608 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5801. Min Range: -8.5801
Max Act: 8.5801. Min Act: -0.1700
Data Index: 8010613 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5801. Min Range: -8.5801
Max Act: 7.9551. Min Act: -0.1700
Data Index: 3603684 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5801. Min Range: -8.5801
Max Act: 7.8301. Min Act: -0.1700
Data Index: 2333751 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5801. Min Range: -8.5801
Max Act: 7.7989. Min Act: -0.1700
Data Index: 6478603 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5801. Min Range: -8.5801
Max Act: 7.7676. Min Act: -0.1700
Data Index: 7522787 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5801. Min Range: -8.5801
Max Act: 7.6739. Min Act: -0.1700
Data Index: 4545968 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5801. Min Range: -8.5801
Max Act: 7.6739. Min Act: -0.1700
Data Index: 2467449 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5801. Min Range: -8.5801
Max Act: 7.6426. Min Act: -0.1700
Data Index: 4146625 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5801. Min Range: -8.5801
Max Act: 7.6114. Min Act: -0.1700
Data Index: 8478886 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5801. Min Range: -8.5801
Max Act: 7.6114. Min Act: -0.1700
Data Index: 5413110 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5801. Min Range: -8.5801
Max Act: 7.5801. Min Act: -0.1700
Data Index: 5863310 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5801. Min Range: -8.5801
Max Act: 7.5801. Min Act: -0.1700
Data Index: 4939969 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5801. Min Range: -8.5801
Max Act: 7.5801. Min Act: -0.1700
Data Index: 6598411 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5801. Min Range: -8.5801
Max Act: 7.5489. Min Act: -0.1700
Data Index: 2704029 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5801. Min Range: -8.5801
Max Act: 7.5176. Min Act: -0.1700
Data Index: 5978605 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5801. Min Range: -8.5801
Max Act: 7.5489. Min Act: -0.1700
Data Index: 5322208 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5801. Min Range: -8.5801
Max Act: 7.5176. Min Act: -0.1700
Data Index: 7675554 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5801. Min Range: -8.5801
Max Act: 7.5176. Min Act: -0.1700
Data Index: 991635 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5801. Min Range: -8.5801
Max Act: 7.5176. Min Act: -0.1700
Data Index: 5789663 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5801. Min Range: -8.5801
Max Act: 7.5176. Min Act: -0.1700
Data Index: 3308189 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19