Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 463 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8519. Min Range: -6.8519
Max Act: 6.8519. Min Act: -0.1700
Data Index: 6091649 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8519. Min Range: -6.8519
Max Act: 6.6957. Min Act: -0.1700
Data Index: 6611669 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8519. Min Range: -6.8519
Max Act: 6.6644. Min Act: -0.1700
Data Index: 5756969 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8519. Min Range: -6.8519
Max Act: 6.5394. Min Act: -0.1700
Data Index: 1055167 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8519. Min Range: -6.8519
Max Act: 6.5394. Min Act: -0.1700
Data Index: 2881735 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8519. Min Range: -6.8519
Max Act: 6.5394. Min Act: -0.1700
Data Index: 4106170 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8519. Min Range: -6.8519
Max Act: 6.3832. Min Act: -0.1700
Data Index: 2695643 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8519. Min Range: -6.8519
Max Act: 6.3832. Min Act: -0.1700
Data Index: 5188654 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8519. Min Range: -6.8519
Max Act: 6.4144. Min Act: -0.1700
Data Index: 1905386 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8519. Min Range: -6.8519
Max Act: 6.3832. Min Act: -0.1700
Data Index: 7770600 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8519. Min Range: -6.8519
Max Act: 6.3519. Min Act: -0.1700
Data Index: 497299 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8519. Min Range: -6.8519
Max Act: 6.3207. Min Act: -0.1700
Data Index: 8824959 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8519. Min Range: -6.8519
Max Act: 6.2894. Min Act: -0.1700
Data Index: 5866464 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8519. Min Range: -6.8519
Max Act: 6.2582. Min Act: -0.1700
Data Index: 2059113 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8519. Min Range: -6.8519
Max Act: 6.2269. Min Act: -0.1700
Data Index: 5329702 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8519. Min Range: -6.8519
Max Act: 6.1644. Min Act: -0.1700
Data Index: 2742220 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8519. Min Range: -6.8519
Max Act: 6.1957. Min Act: -0.1700
Data Index: 2130999 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8519. Min Range: -6.8519
Max Act: 6.1644. Min Act: -0.1700
Data Index: 1663685 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8519. Min Range: -6.8519
Max Act: 6.1644. Min Act: -0.1700
Data Index: 8604819 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8519. Min Range: -6.8519
Max Act: 6.1332. Min Act: -0.1700
Data Index: 370959 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19