Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3568 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7170. Min Range: -4.7170
Max Act: 4.7170. Min Act: -0.1700
Data Index: 8024036 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7170. Min Range: -4.7170
Max Act: 4.6858. Min Act: -0.1700
Data Index: 8592436 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7170. Min Range: -4.7170
Max Act: 4.5608. Min Act: -0.1700
Data Index: 8703816 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7170. Min Range: -4.7170
Max Act: 4.5920. Min Act: -0.1700
Data Index: 1013914 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7170. Min Range: -4.7170
Max Act: 4.5608. Min Act: -0.1700
Data Index: 5667075 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7170. Min Range: -4.7170
Max Act: 4.5295. Min Act: -0.1700
Data Index: 3267011 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7170. Min Range: -4.7170
Max Act: 4.5295. Min Act: -0.1700
Data Index: 194478 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7170. Min Range: -4.7170
Max Act: 4.4983. Min Act: -0.1700
Data Index: 524333 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7170. Min Range: -4.7170
Max Act: 4.4983. Min Act: -0.1700
Data Index: 3347509 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7170. Min Range: -4.7170
Max Act: 4.4983. Min Act: -0.1700
Data Index: 8387905 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7170. Min Range: -4.7170
Max Act: 4.4670. Min Act: -0.1700
Data Index: 3424933 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7170. Min Range: -4.7170
Max Act: 4.4670. Min Act: -0.1700
Data Index: 5312593 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7170. Min Range: -4.7170
Max Act: 4.4670. Min Act: -0.1700
Data Index: 8760640 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7170. Min Range: -4.7170
Max Act: 4.4358. Min Act: -0.1700
Data Index: 2898305 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7170. Min Range: -4.7170
Max Act: 4.4358. Min Act: -0.1700
Data Index: 5056332 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7170. Min Range: -4.7170
Max Act: 4.4358. Min Act: -0.1700
Data Index: 6115446 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7170. Min Range: -4.7170
Max Act: 4.4358. Min Act: -0.1700
Data Index: 1498505 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7170. Min Range: -4.7170
Max Act: 4.4358. Min Act: -0.1700
Data Index: 5575236 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7170. Min Range: -4.7170
Max Act: 4.4358. Min Act: -0.1700
Data Index: 2523820 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7170. Min Range: -4.7170
Max Act: 4.4358. Min Act: -0.1700
Data Index: 1063378 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19