Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2825 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9365. Min Range: -4.9365
Max Act: 4.9365. Min Act: -0.1700
Data Index: 5858951 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9365. Min Range: -4.9365
Max Act: 4.7803. Min Act: -0.1700
Data Index: 4795283 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9365. Min Range: -4.9365
Max Act: 4.7803. Min Act: -0.1700
Data Index: 8275747 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9365. Min Range: -4.9365
Max Act: 4.7803. Min Act: -0.1700
Data Index: 5207426 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9365. Min Range: -4.9365
Max Act: 4.7803. Min Act: -0.1700
Data Index: 410936 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9365. Min Range: -4.9365
Max Act: 4.7490. Min Act: -0.1700
Data Index: 5289539 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9365. Min Range: -4.9365
Max Act: 4.7490. Min Act: -0.1700
Data Index: 5889766 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9365. Min Range: -4.9365
Max Act: 4.7490. Min Act: -0.1700
Data Index: 397926 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9365. Min Range: -4.9365
Max Act: 4.7178. Min Act: -0.1700
Data Index: 3403089 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9365. Min Range: -4.9365
Max Act: 4.6865. Min Act: -0.1700
Data Index: 1163361 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9365. Min Range: -4.9365
Max Act: 4.7178. Min Act: -0.1700
Data Index: 855680 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9365. Min Range: -4.9365
Max Act: 4.7178. Min Act: -0.1700
Data Index: 4293954 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9365. Min Range: -4.9365
Max Act: 4.7178. Min Act: -0.1700
Data Index: 5012474 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9365. Min Range: -4.9365
Max Act: 4.7178. Min Act: -0.1700
Data Index: 8108973 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9365. Min Range: -4.9365
Max Act: 4.7178. Min Act: -0.1700
Data Index: 5470776 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9365. Min Range: -4.9365
Max Act: 4.6865. Min Act: -0.1700
Data Index: 5061341 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9365. Min Range: -4.9365
Max Act: 4.7178. Min Act: -0.1700
Data Index: 1964163 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9365. Min Range: -4.9365
Max Act: 4.6865. Min Act: -0.1700
Data Index: 5139760 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9365. Min Range: -4.9365
Max Act: 4.6865. Min Act: -0.1700
Data Index: 2816352 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9365. Min Range: -4.9365
Max Act: 4.6865. Min Act: -0.1700
Data Index: 3398820 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19