Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1340 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1683. Min Range: -10.1683
Max Act: 10.1683. Min Act: -0.1700
Data Index: 4140692 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1683. Min Range: -10.1683
Max Act: 10.1058. Min Act: -0.1700
Data Index: 5429922 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1683. Min Range: -10.1683
Max Act: 10.1058. Min Act: -0.1700
Data Index: 2845384 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1683. Min Range: -10.1683
Max Act: 10.0433. Min Act: -0.1700
Data Index: 1900841 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1683. Min Range: -10.1683
Max Act: 10.0433. Min Act: -0.1700
Data Index: 7845285 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1683. Min Range: -10.1683
Max Act: 9.9808. Min Act: -0.1700
Data Index: 3318091 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1683. Min Range: -10.1683
Max Act: 9.8558. Min Act: -0.1700
Data Index: 2370882 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1683. Min Range: -10.1683
Max Act: 9.9183. Min Act: -0.1700
Data Index: 8241117 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1683. Min Range: -10.1683
Max Act: 9.8558. Min Act: -0.1700
Data Index: 6666328 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1683. Min Range: -10.1683
Max Act: 9.8558. Min Act: -0.1700
Data Index: 4628963 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1683. Min Range: -10.1683
Max Act: 9.8558. Min Act: -0.1700
Data Index: 7900 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1683. Min Range: -10.1683
Max Act: 9.7308. Min Act: -0.1700
Data Index: 2282475 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1683. Min Range: -10.1683
Max Act: 9.7933. Min Act: -0.1700
Data Index: 7461312 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1683. Min Range: -10.1683
Max Act: 9.7933. Min Act: -0.1700
Data Index: 6786193 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1683. Min Range: -10.1683
Max Act: 9.7308. Min Act: -0.1700
Data Index: 6136521 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1683. Min Range: -10.1683
Max Act: 9.7308. Min Act: -0.1700
Data Index: 5823585 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1683. Min Range: -10.1683
Max Act: 9.7308. Min Act: -0.1700
Data Index: 4079957 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1683. Min Range: -10.1683
Max Act: 9.7308. Min Act: -0.1700
Data Index: 2419511 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1683. Min Range: -10.1683
Max Act: 9.7308. Min Act: -0.1700
Data Index: 8733723 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1683. Min Range: -10.1683
Max Act: 9.7308. Min Act: -0.1700
Data Index: 6357794 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19