Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4042 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2810. Min Range: -5.2810
Max Act: 5.2810. Min Act: -0.1700
Data Index: 5232420 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2810. Min Range: -5.2810
Max Act: 5.2810. Min Act: -0.1700
Data Index: 4829107 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2810. Min Range: -5.2810
Max Act: 5.2497. Min Act: -0.1700
Data Index: 258383 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2810. Min Range: -5.2810
Max Act: 5.2497. Min Act: -0.1700
Data Index: 4729458 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2810. Min Range: -5.2810
Max Act: 5.2185. Min Act: -0.1700
Data Index: 6445162 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2810. Min Range: -5.2810
Max Act: 5.2185. Min Act: -0.1700
Data Index: 588458 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2810. Min Range: -5.2810
Max Act: 5.1872. Min Act: -0.1700
Data Index: 6966929 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2810. Min Range: -5.2810
Max Act: 5.1872. Min Act: -0.1700
Data Index: 810684 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2810. Min Range: -5.2810
Max Act: 5.1247. Min Act: -0.1700
Data Index: 5546410 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2810. Min Range: -5.2810
Max Act: 5.1247. Min Act: -0.1700
Data Index: 3735881 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2810. Min Range: -5.2810
Max Act: 5.1247. Min Act: -0.1700
Data Index: 7521453 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2810. Min Range: -5.2810
Max Act: 5.0935. Min Act: -0.1700
Data Index: 4028869 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2810. Min Range: -5.2810
Max Act: 5.0935. Min Act: -0.1700
Data Index: 2726149 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2810. Min Range: -5.2810
Max Act: 5.0935. Min Act: -0.1700
Data Index: 6946863 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2810. Min Range: -5.2810
Max Act: 5.0935. Min Act: -0.1700
Data Index: 8815416 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2810. Min Range: -5.2810
Max Act: 5.0622. Min Act: -0.1700
Data Index: 2534556 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2810. Min Range: -5.2810
Max Act: 5.0622. Min Act: -0.1700
Data Index: 4987605 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2810. Min Range: -5.2810
Max Act: 5.0622. Min Act: -0.1700
Data Index: 997984 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2810. Min Range: -5.2810
Max Act: 5.0622. Min Act: -0.1700
Data Index: 272340 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2810. Min Range: -5.2810
Max Act: 5.0622. Min Act: -0.1700
Data Index: 4559184 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19