Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2121 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7506. Min Range: -5.7506
Max Act: 5.7506. Min Act: -0.1700
Data Index: 7054171 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7506. Min Range: -5.7506
Max Act: 5.7193. Min Act: -0.1700
Data Index: 831830 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7506. Min Range: -5.7506
Max Act: 5.6256. Min Act: -0.1700
Data Index: 4626080 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7506. Min Range: -5.7506
Max Act: 5.6256. Min Act: -0.1700
Data Index: 4076695 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7506. Min Range: -5.7506
Max Act: 5.5318. Min Act: -0.1700
Data Index: 7247837 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7506. Min Range: -5.7506
Max Act: 5.5006. Min Act: -0.1700
Data Index: 6846907 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7506. Min Range: -5.7506
Max Act: 5.4693. Min Act: -0.1700
Data Index: 8506429 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7506. Min Range: -5.7506
Max Act: 5.4693. Min Act: -0.1700
Data Index: 4474593 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7506. Min Range: -5.7506
Max Act: 5.4693. Min Act: -0.1700
Data Index: 5598799 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7506. Min Range: -5.7506
Max Act: 5.4381. Min Act: -0.1700
Data Index: 2092398 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7506. Min Range: -5.7506
Max Act: 5.4381. Min Act: -0.1700
Data Index: 5437448 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7506. Min Range: -5.7506
Max Act: 5.4068. Min Act: -0.1700
Data Index: 4162848 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7506. Min Range: -5.7506
Max Act: 5.4068. Min Act: -0.1700
Data Index: 8360846 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7506. Min Range: -5.7506
Max Act: 5.4068. Min Act: -0.1700
Data Index: 1426789 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7506. Min Range: -5.7506
Max Act: 5.3756. Min Act: -0.1700
Data Index: 3719777 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7506. Min Range: -5.7506
Max Act: 5.3756. Min Act: -0.1700
Data Index: 7346998 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7506. Min Range: -5.7506
Max Act: 5.3756. Min Act: -0.1700
Data Index: 3578846 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7506. Min Range: -5.7506
Max Act: 5.3131. Min Act: -0.1700
Data Index: 3727877 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7506. Min Range: -5.7506
Max Act: 5.3756. Min Act: -0.1700
Data Index: 3890648 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7506. Min Range: -5.7506
Max Act: 5.3443. Min Act: -0.1700
Data Index: 1101689 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19