Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 264 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1983. Min Range: -8.1983
Max Act: 8.1983. Min Act: -0.1700
Data Index: 5453482 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1983. Min Range: -8.1983
Max Act: 8.1983. Min Act: -0.1700
Data Index: 2181719 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1983. Min Range: -8.1983
Max Act: 7.8545. Min Act: -0.1700
Data Index: 6291293 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1983. Min Range: -8.1983
Max Act: 7.7608. Min Act: -0.1700
Data Index: 3741460 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1983. Min Range: -8.1983
Max Act: 7.7295. Min Act: -0.1700
Data Index: 518806 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1983. Min Range: -8.1983
Max Act: 7.6983. Min Act: -0.1700
Data Index: 2475745 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1983. Min Range: -8.1983
Max Act: 7.6983. Min Act: -0.1700
Data Index: 4659588 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1983. Min Range: -8.1983
Max Act: 7.6670. Min Act: -0.1700
Data Index: 1319893 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1983. Min Range: -8.1983
Max Act: 7.6358. Min Act: -0.1700
Data Index: 1754826 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1983. Min Range: -8.1983
Max Act: 7.6045. Min Act: -0.1700
Data Index: 8130035 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1983. Min Range: -8.1983
Max Act: 7.5733. Min Act: -0.1700
Data Index: 2722614 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1983. Min Range: -8.1983
Max Act: 7.5420. Min Act: -0.1700
Data Index: 5893548 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1983. Min Range: -8.1983
Max Act: 7.5420. Min Act: -0.1700
Data Index: 7152669 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1983. Min Range: -8.1983
Max Act: 7.5108. Min Act: -0.1700
Data Index: 5484566 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1983. Min Range: -8.1983
Max Act: 7.4795. Min Act: -0.1700
Data Index: 727847 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1983. Min Range: -8.1983
Max Act: 7.4795. Min Act: -0.1700
Data Index: 3294464 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1983. Min Range: -8.1983
Max Act: 7.4483. Min Act: -0.1700
Data Index: 6657240 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1983. Min Range: -8.1983
Max Act: 7.4483. Min Act: -0.1700
Data Index: 2709109 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1983. Min Range: -8.1983
Max Act: 7.4483. Min Act: -0.1700
Data Index: 3428215 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1983. Min Range: -8.1983
Max Act: 7.4483. Min Act: -0.1700
Data Index: 1018648 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19