Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2630 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4332. Min Range: -8.4332
Max Act: 8.4332. Min Act: -0.1700
Data Index: 1260490 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4332. Min Range: -8.4332
Max Act: 8.3707. Min Act: -0.1700
Data Index: 576611 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4332. Min Range: -8.4332
Max Act: 8.3082. Min Act: -0.1699
Data Index: 6676908 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4332. Min Range: -8.4332
Max Act: 8.3082. Min Act: -0.1699
Data Index: 8402293 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4332. Min Range: -8.4332
Max Act: 8.2457. Min Act: -0.1700
Data Index: 6738537 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4332. Min Range: -8.4332
Max Act: 8.2457. Min Act: -0.1700
Data Index: 5391458 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4332. Min Range: -8.4332
Max Act: 8.2457. Min Act: -0.1699
Data Index: 4507665 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4332. Min Range: -8.4332
Max Act: 8.1832. Min Act: -0.1700
Data Index: 2225133 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4332. Min Range: -8.4332
Max Act: 8.2457. Min Act: -0.1699
Data Index: 4207154 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4332. Min Range: -8.4332
Max Act: 8.2457. Min Act: -0.1700
Data Index: 8536849 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4332. Min Range: -8.4332
Max Act: 8.2457. Min Act: -0.1700
Data Index: 3715837 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4332. Min Range: -8.4332
Max Act: 8.2457. Min Act: -0.1700
Data Index: 7923198 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4332. Min Range: -8.4332
Max Act: 8.2457. Min Act: -0.1699
Data Index: 7506070 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4332. Min Range: -8.4332
Max Act: 8.2457. Min Act: -0.1692
Data Index: 3390037 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4332. Min Range: -8.4332
Max Act: 8.2457. Min Act: -0.1700
Data Index: 3277130 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4332. Min Range: -8.4332
Max Act: 8.1832. Min Act: -0.1700
Data Index: 4149605 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4332. Min Range: -8.4332
Max Act: 8.1832. Min Act: -0.1699
Data Index: 4187059 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4332. Min Range: -8.4332
Max Act: 8.1207. Min Act: -0.1699
Data Index: 4313401 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4332. Min Range: -8.4332
Max Act: 8.1832. Min Act: -0.1700
Data Index: 2344719 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4332. Min Range: -8.4332
Max Act: 8.1832. Min Act: -0.1684
Data Index: 5271953 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19