Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2705 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3033. Min Range: -7.3033
Max Act: 7.3033. Min Act: -0.1700
Data Index: 7899359 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3033. Min Range: -7.3033
Max Act: 7.2408. Min Act: -0.1700
Data Index: 7088915 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3033. Min Range: -7.3033
Max Act: 7.1783. Min Act: -0.1700
Data Index: 7508637 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3033. Min Range: -7.3033
Max Act: 7.1783. Min Act: -0.1700
Data Index: 4506943 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3033. Min Range: -7.3033
Max Act: 7.1470. Min Act: -0.1700
Data Index: 7551510 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3033. Min Range: -7.3033
Max Act: 7.1470. Min Act: -0.1700
Data Index: 6583881 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3033. Min Range: -7.3033
Max Act: 7.1158. Min Act: -0.1700
Data Index: 1737526 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3033. Min Range: -7.3033
Max Act: 7.0845. Min Act: -0.1700
Data Index: 7206824 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3033. Min Range: -7.3033
Max Act: 7.0533. Min Act: -0.1700
Data Index: 3889881 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3033. Min Range: -7.3033
Max Act: 7.0533. Min Act: -0.1700
Data Index: 2191412 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3033. Min Range: -7.3033
Max Act: 7.0220. Min Act: -0.1700
Data Index: 3582670 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3033. Min Range: -7.3033
Max Act: 6.9908. Min Act: -0.1700
Data Index: 8502022 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3033. Min Range: -7.3033
Max Act: 7.0220. Min Act: -0.1700
Data Index: 1879401 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3033. Min Range: -7.3033
Max Act: 6.9595. Min Act: -0.1700
Data Index: 6842448 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3033. Min Range: -7.3033
Max Act: 6.9595. Min Act: -0.1700
Data Index: 5987115 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3033. Min Range: -7.3033
Max Act: 6.8970. Min Act: -0.1700
Data Index: 711210 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3033. Min Range: -7.3033
Max Act: 6.8970. Min Act: -0.1700
Data Index: 4254241 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3033. Min Range: -7.3033
Max Act: 6.8970. Min Act: -0.1700
Data Index: 2015762 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3033. Min Range: -7.3033
Max Act: 6.8970. Min Act: -0.1700
Data Index: 7303414 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3033. Min Range: -7.3033
Max Act: 6.8658. Min Act: -0.1700
Data Index: 6309048 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19