Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5289 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1689. Min Range: -7.1689
Max Act: 7.1689. Min Act: -0.1700
Data Index: 6330058 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1689. Min Range: -7.1689
Max Act: 7.0127. Min Act: -0.1700
Data Index: 3236119 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1689. Min Range: -7.1689
Max Act: 6.9502. Min Act: -0.1700
Data Index: 4867784 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1689. Min Range: -7.1689
Max Act: 6.9502. Min Act: -0.1700
Data Index: 3614053 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1689. Min Range: -7.1689
Max Act: 6.8877. Min Act: -0.1700
Data Index: 1560641 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1689. Min Range: -7.1689
Max Act: 6.8877. Min Act: -0.1700
Data Index: 7642548 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1689. Min Range: -7.1689
Max Act: 6.8564. Min Act: -0.1700
Data Index: 8477728 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1689. Min Range: -7.1689
Max Act: 6.8564. Min Act: -0.1700
Data Index: 1850825 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1689. Min Range: -7.1689
Max Act: 6.7939. Min Act: -0.1700
Data Index: 6107568 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1689. Min Range: -7.1689
Max Act: 6.7314. Min Act: -0.1700
Data Index: 2190801 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1689. Min Range: -7.1689
Max Act: 6.7314. Min Act: -0.1700
Data Index: 841891 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1689. Min Range: -7.1689
Max Act: 6.7002. Min Act: -0.1700
Data Index: 2532291 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1689. Min Range: -7.1689
Max Act: 6.6689. Min Act: -0.1700
Data Index: 937901 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1689. Min Range: -7.1689
Max Act: 6.6689. Min Act: -0.1700
Data Index: 3730319 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1689. Min Range: -7.1689
Max Act: 6.6064. Min Act: -0.1700
Data Index: 8726765 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1689. Min Range: -7.1689
Max Act: 6.6064. Min Act: -0.1700
Data Index: 3193673 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1689. Min Range: -7.1689
Max Act: 6.5752. Min Act: -0.1700
Data Index: 4537477 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1689. Min Range: -7.1689
Max Act: 6.6064. Min Act: -0.1700
Data Index: 8081538 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1689. Min Range: -7.1689
Max Act: 6.5439. Min Act: -0.1700
Data Index: 6858349 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1689. Min Range: -7.1689
Max Act: 6.5752. Min Act: -0.1700
Data Index: 3550105 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19