Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1904 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9703. Min Range: -2.9703
Max Act: 2.9703. Min Act: -0.1700
Data Index: 5315921 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9703. Min Range: -2.9703
Max Act: 2.9545. Min Act: -0.1700
Data Index: 6199527 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9703. Min Range: -2.9703
Max Act: 2.8594. Min Act: -0.1700
Data Index: 509490 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9703. Min Range: -2.9703
Max Act: 2.8435. Min Act: -0.1700
Data Index: 1900466 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9703. Min Range: -2.9703
Max Act: 2.8276. Min Act: -0.1700
Data Index: 2727275 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9703. Min Range: -2.9703
Max Act: 2.8276. Min Act: -0.1700
Data Index: 2017355 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9703. Min Range: -2.9703
Max Act: 2.8276. Min Act: -0.1700
Data Index: 1464339 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9703. Min Range: -2.9703
Max Act: 2.8117. Min Act: -0.1700
Data Index: 2918213 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9703. Min Range: -2.9703
Max Act: 2.8117. Min Act: -0.1700
Data Index: 7338704 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9703. Min Range: -2.9703
Max Act: 2.7798. Min Act: -0.1700
Data Index: 5038039 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9703. Min Range: -2.9703
Max Act: 2.7798. Min Act: -0.1700
Data Index: 7377186 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9703. Min Range: -2.9703
Max Act: 2.7639. Min Act: -0.1700
Data Index: 1619899 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9703. Min Range: -2.9703
Max Act: 2.7639. Min Act: -0.1700
Data Index: 5302584 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9703. Min Range: -2.9703
Max Act: 2.7479. Min Act: -0.1700
Data Index: 7809359 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9703. Min Range: -2.9703
Max Act: 2.7479. Min Act: -0.1700
Data Index: 5545325 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9703. Min Range: -2.9703
Max Act: 2.7479. Min Act: -0.1700
Data Index: 4535218 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9703. Min Range: -2.9703
Max Act: 2.7479. Min Act: -0.1700
Data Index: 5846027 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9703. Min Range: -2.9703
Max Act: 2.7479. Min Act: -0.1700
Data Index: 5391225 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9703. Min Range: -2.9703
Max Act: 2.7479. Min Act: -0.1700
Data Index: 7864137 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9703. Min Range: -2.9703
Max Act: 2.7319. Min Act: -0.1700
Data Index: 6445352 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19