Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2062 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9537. Min Range: -5.9537
Max Act: 5.9537. Min Act: -0.1700
Data Index: 1965045 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9537. Min Range: -5.9537
Max Act: 5.8600. Min Act: -0.1699
Data Index: 1414020 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9537. Min Range: -5.9537
Max Act: 5.7975. Min Act: -0.1699
Data Index: 1414023 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9537. Min Range: -5.9537
Max Act: 5.7662. Min Act: -0.1700
Data Index: 1414021 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9537. Min Range: -5.9537
Max Act: 5.7350. Min Act: -0.1700
Data Index: 1414018 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9537. Min Range: -5.9537
Max Act: 5.7037. Min Act: -0.1700
Data Index: 8406824 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9537. Min Range: -5.9537
Max Act: 5.7037. Min Act: -0.1700
Data Index: 4876095 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9537. Min Range: -5.9537
Max Act: 5.7037. Min Act: -0.1700
Data Index: 1414008 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9537. Min Range: -5.9537
Max Act: 5.7037. Min Act: -0.1700
Data Index: 5767466 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9537. Min Range: -5.9537
Max Act: 5.7037. Min Act: -0.1700
Data Index: 7657010 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9537. Min Range: -5.9537
Max Act: 5.6725. Min Act: -0.1700
Data Index: 1196319 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9537. Min Range: -5.9537
Max Act: 5.6725. Min Act: -0.1700
Data Index: 3757536 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9537. Min Range: -5.9537
Max Act: 5.6725. Min Act: -0.1700
Data Index: 4254142 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9537. Min Range: -5.9537
Max Act: 5.6100. Min Act: -0.1700
Data Index: 840416 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9537. Min Range: -5.9537
Max Act: 5.6412. Min Act: -0.1700
Data Index: 6748245 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9537. Min Range: -5.9537
Max Act: 5.6725. Min Act: -0.1700
Data Index: 1414017 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9537. Min Range: -5.9537
Max Act: 5.6412. Min Act: -0.1700
Data Index: 5697242 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9537. Min Range: -5.9537
Max Act: 5.6412. Min Act: -0.1700
Data Index: 6564520 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9537. Min Range: -5.9537
Max Act: 5.6412. Min Act: -0.1700
Data Index: 6748241 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9537. Min Range: -5.9537
Max Act: 5.6100. Min Act: -0.1700
Data Index: 5053388 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19