Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 26 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9170. Min Range: -6.9170
Max Act: 6.9170. Min Act: -0.1700
Data Index: 8673359 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9170. Min Range: -6.9170
Max Act: 6.5733. Min Act: -0.1700
Data Index: 4572562 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9170. Min Range: -6.9170
Max Act: 6.5108. Min Act: -0.1700
Data Index: 2599405 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9170. Min Range: -6.9170
Max Act: 6.4795. Min Act: -0.1700
Data Index: 69818 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9170. Min Range: -6.9170
Max Act: 6.4483. Min Act: -0.1700
Data Index: 2174540 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9170. Min Range: -6.9170
Max Act: 6.3858. Min Act: -0.1700
Data Index: 4022763 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9170. Min Range: -6.9170
Max Act: 6.3545. Min Act: -0.1700
Data Index: 5124742 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9170. Min Range: -6.9170
Max Act: 6.3233. Min Act: -0.1700
Data Index: 4843977 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9170. Min Range: -6.9170
Max Act: 6.2920. Min Act: -0.1700
Data Index: 3243612 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9170. Min Range: -6.9170
Max Act: 6.2608. Min Act: -0.1700
Data Index: 778758 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9170. Min Range: -6.9170
Max Act: 6.2920. Min Act: -0.1700
Data Index: 3039876 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9170. Min Range: -6.9170
Max Act: 6.2295. Min Act: -0.1700
Data Index: 8613320 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9170. Min Range: -6.9170
Max Act: 6.1983. Min Act: -0.1700
Data Index: 2465597 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9170. Min Range: -6.9170
Max Act: 6.2295. Min Act: -0.1700
Data Index: 6364178 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9170. Min Range: -6.9170
Max Act: 6.1983. Min Act: -0.1700
Data Index: 1327836 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9170. Min Range: -6.9170
Max Act: 6.1983. Min Act: -0.1700
Data Index: 7297383 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9170. Min Range: -6.9170
Max Act: 6.1983. Min Act: -0.1700
Data Index: 7039345 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9170. Min Range: -6.9170
Max Act: 6.1983. Min Act: -0.1700
Data Index: 5096581 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9170. Min Range: -6.9170
Max Act: 6.1670. Min Act: -0.1700
Data Index: 2491978 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9170. Min Range: -6.9170
Max Act: 6.1670. Min Act: -0.1700
Data Index: 4059055 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19