Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2881 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.8586. Min Act: -0.1700
Data Index: 1547424 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.7961. Min Act: -0.1700
Data Index: 1111808 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.7961. Min Act: -0.1700
Data Index: 8184710 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.7336. Min Act: -0.1700
Data Index: 3141217 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.6086. Min Act: -0.1700
Data Index: 4876772 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.6086. Min Act: -0.1700
Data Index: 1335656 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.5461. Min Act: -0.1700
Data Index: 1686611 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.5461. Min Act: -0.1700
Data Index: 3031639 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.5461. Min Act: -0.1700
Data Index: 3981154 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.4836. Min Act: -0.1700
Data Index: 1824914 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.5461. Min Act: -0.1700
Data Index: 8123374 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.4836. Min Act: -0.1700
Data Index: 8249192 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.4836. Min Act: -0.1700
Data Index: 6123608 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.4836. Min Act: -0.1700
Data Index: 1249249 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.4211. Min Act: -0.1700
Data Index: 684976 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.4211. Min Act: -0.1700
Data Index: 8689976 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.4211. Min Act: -0.1700
Data Index: 1148917 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.4211. Min Act: -0.1700
Data Index: 2487810 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.3586. Min Act: -0.1700
Data Index: 3728350 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.3586. Min Act: -0.1700
Data Index: 3890597 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19