Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 896 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0703. Min Range: -6.0703
Max Act: 6.0703. Min Act: -0.1700
Data Index: 1760555 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0703. Min Range: -6.0703
Max Act: 6.0078. Min Act: -0.1700
Data Index: 8376593 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0703. Min Range: -6.0703
Max Act: 5.9140. Min Act: -0.1700
Data Index: 1704779 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0703. Min Range: -6.0703
Max Act: 5.8515. Min Act: -0.1700
Data Index: 2420358 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0703. Min Range: -6.0703
Max Act: 5.8203. Min Act: -0.1700
Data Index: 843035 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0703. Min Range: -6.0703
Max Act: 5.7890. Min Act: -0.1700
Data Index: 7688955 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0703. Min Range: -6.0703
Max Act: 5.8203. Min Act: -0.1700
Data Index: 1643065 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0703. Min Range: -6.0703
Max Act: 5.7578. Min Act: -0.1700
Data Index: 6849289 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0703. Min Range: -6.0703
Max Act: 5.6953. Min Act: -0.1700
Data Index: 2331873 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0703. Min Range: -6.0703
Max Act: 5.6953. Min Act: -0.1700
Data Index: 7694700 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0703. Min Range: -6.0703
Max Act: 5.6953. Min Act: -0.1700
Data Index: 2505124 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0703. Min Range: -6.0703
Max Act: 5.6640. Min Act: -0.1700
Data Index: 3911026 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0703. Min Range: -6.0703
Max Act: 5.6640. Min Act: -0.1700
Data Index: 4933080 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0703. Min Range: -6.0703
Max Act: 5.6640. Min Act: -0.1700
Data Index: 4847493 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0703. Min Range: -6.0703
Max Act: 5.6328. Min Act: -0.1700
Data Index: 5016985 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0703. Min Range: -6.0703
Max Act: 5.6015. Min Act: -0.1700
Data Index: 3229114 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0703. Min Range: -6.0703
Max Act: 5.6328. Min Act: -0.1700
Data Index: 1681570 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0703. Min Range: -6.0703
Max Act: 5.6015. Min Act: -0.1700
Data Index: 5191567 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0703. Min Range: -6.0703
Max Act: 5.5703. Min Act: -0.1700
Data Index: 967937 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0703. Min Range: -6.0703
Max Act: 5.6328. Min Act: -0.1700
Data Index: 321657 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19