Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6270 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7506. Min Range: -4.7506
Max Act: 4.7506. Min Act: -0.1700
Data Index: 1471877 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7506. Min Range: -4.7506
Max Act: 4.6881. Min Act: -0.1700
Data Index: 2788152 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7506. Min Range: -4.7506
Max Act: 4.6256. Min Act: -0.1700
Data Index: 1104684 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7506. Min Range: -4.7506
Max Act: 4.5944. Min Act: -0.1700
Data Index: 3178245 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7506. Min Range: -4.7506
Max Act: 4.5944. Min Act: -0.1700
Data Index: 3962532 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7506. Min Range: -4.7506
Max Act: 4.5944. Min Act: -0.1700
Data Index: 4875011 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7506. Min Range: -4.7506
Max Act: 4.5631. Min Act: -0.1700
Data Index: 4231491 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7506. Min Range: -4.7506
Max Act: 4.5631. Min Act: -0.1700
Data Index: 2124189 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7506. Min Range: -4.7506
Max Act: 4.5319. Min Act: -0.1700
Data Index: 3418226 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7506. Min Range: -4.7506
Max Act: 4.5319. Min Act: -0.1700
Data Index: 7412801 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7506. Min Range: -4.7506
Max Act: 4.5006. Min Act: -0.1700
Data Index: 4268239 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7506. Min Range: -4.7506
Max Act: 4.5006. Min Act: -0.1700
Data Index: 8221352 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7506. Min Range: -4.7506
Max Act: 4.5006. Min Act: -0.1700
Data Index: 90759 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7506. Min Range: -4.7506
Max Act: 4.5006. Min Act: -0.1700
Data Index: 8354406 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7506. Min Range: -4.7506
Max Act: 4.5319. Min Act: -0.1700
Data Index: 5528684 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7506. Min Range: -4.7506
Max Act: 4.5006. Min Act: -0.1700
Data Index: 2058422 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7506. Min Range: -4.7506
Max Act: 4.5006. Min Act: -0.1700
Data Index: 2684821 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7506. Min Range: -4.7506
Max Act: 4.5006. Min Act: -0.1700
Data Index: 7978536 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7506. Min Range: -4.7506
Max Act: 4.4694. Min Act: -0.1700
Data Index: 5969041 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7506. Min Range: -4.7506
Max Act: 4.4694. Min Act: -0.1700
Data Index: 1804953 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19