Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4593 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6105. Min Range: -5.6105
Max Act: 5.6105. Min Act: -0.1700
Data Index: 6713889 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6105. Min Range: -5.6105
Max Act: 5.5793. Min Act: -0.1700
Data Index: 1330071 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6105. Min Range: -5.6105
Max Act: 5.5480. Min Act: -0.1700
Data Index: 3502243 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6105. Min Range: -5.6105
Max Act: 5.4855. Min Act: -0.1700
Data Index: 4978688 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6105. Min Range: -5.6105
Max Act: 5.5168. Min Act: -0.1700
Data Index: 8003147 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6105. Min Range: -5.6105
Max Act: 5.4855. Min Act: -0.1700
Data Index: 5774660 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6105. Min Range: -5.6105
Max Act: 5.4855. Min Act: -0.1700
Data Index: 20501 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6105. Min Range: -5.6105
Max Act: 5.4855. Min Act: -0.1700
Data Index: 4593154 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6105. Min Range: -5.6105
Max Act: 5.4543. Min Act: -0.1700
Data Index: 7222999 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6105. Min Range: -5.6105
Max Act: 5.4543. Min Act: -0.1700
Data Index: 2699314 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6105. Min Range: -5.6105
Max Act: 5.4230. Min Act: -0.1700
Data Index: 6920152 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6105. Min Range: -5.6105
Max Act: 5.4230. Min Act: -0.1700
Data Index: 7048177 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6105. Min Range: -5.6105
Max Act: 5.4230. Min Act: -0.1700
Data Index: 7409368 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6105. Min Range: -5.6105
Max Act: 5.4230. Min Act: -0.1700
Data Index: 4904261 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6105. Min Range: -5.6105
Max Act: 5.4230. Min Act: -0.1700
Data Index: 7090241 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6105. Min Range: -5.6105
Max Act: 5.4230. Min Act: -0.1700
Data Index: 998574 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6105. Min Range: -5.6105
Max Act: 5.3918. Min Act: -0.1700
Data Index: 7234424 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6105. Min Range: -5.6105
Max Act: 5.3605. Min Act: -0.1700
Data Index: 8170094 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6105. Min Range: -5.6105
Max Act: 5.3918. Min Act: -0.1700
Data Index: 5636433 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6105. Min Range: -5.6105
Max Act: 5.3605. Min Act: -0.1700
Data Index: 5637500 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19