Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 31 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4447. Min Range: -8.4447
Max Act: 8.4447. Min Act: -0.1700
Data Index: 1425065 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4447. Min Range: -8.4447
Max Act: 8.4447. Min Act: -0.1700
Data Index: 5272422 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4447. Min Range: -8.4447
Max Act: 8.2572. Min Act: -0.1700
Data Index: 6052756 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4447. Min Range: -8.4447
Max Act: 8.1947. Min Act: -0.1700
Data Index: 1434664 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4447. Min Range: -8.4447
Max Act: 8.1322. Min Act: -0.1700
Data Index: 311291 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4447. Min Range: -8.4447
Max Act: 8.0697. Min Act: -0.1700
Data Index: 8544104 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4447. Min Range: -8.4447
Max Act: 8.0697. Min Act: -0.1700
Data Index: 4153522 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4447. Min Range: -8.4447
Max Act: 7.9447. Min Act: -0.1700
Data Index: 1754160 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4447. Min Range: -8.4447
Max Act: 7.9447. Min Act: -0.1700
Data Index: 8295822 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4447. Min Range: -8.4447
Max Act: 7.8822. Min Act: -0.1700
Data Index: 3699018 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4447. Min Range: -8.4447
Max Act: 7.8822. Min Act: -0.1700
Data Index: 311290 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4447. Min Range: -8.4447
Max Act: 7.8822. Min Act: -0.1700
Data Index: 7216017 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4447. Min Range: -8.4447
Max Act: 7.8822. Min Act: -0.1700
Data Index: 7150570 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4447. Min Range: -8.4447
Max Act: 7.8197. Min Act: -0.1700
Data Index: 5577468 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4447. Min Range: -8.4447
Max Act: 7.7572. Min Act: -0.1700
Data Index: 5109543 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4447. Min Range: -8.4447
Max Act: 7.7572. Min Act: -0.1700
Data Index: 3804560 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4447. Min Range: -8.4447
Max Act: 7.6947. Min Act: -0.1700
Data Index: 4630194 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4447. Min Range: -8.4447
Max Act: 7.6947. Min Act: -0.1700
Data Index: 8136546 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4447. Min Range: -8.4447
Max Act: 7.6947. Min Act: -0.1700
Data Index: 6499932 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4447. Min Range: -8.4447
Max Act: 7.6947. Min Act: -0.1700
Data Index: 7183173 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19