Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2840 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0600. Min Range: -1.0600
Max Act: 1.0600. Min Act: -0.1690
Data Index: 3944399 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0600. Min Range: -1.0600
Max Act: 1.0600. Min Act: -0.1699
Data Index: 1249748 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0600. Min Range: -1.0600
Max Act: 1.0600. Min Act: -0.1700
Data Index: 746821 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0600. Min Range: -1.0600
Max Act: 0.9731. Min Act: -0.1700
Data Index: 2311193 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0600. Min Range: -1.0600
Max Act: 0.9817. Min Act: -0.1700
Data Index: 2247630 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0600. Min Range: -1.0600
Max Act: 0.9817. Min Act: -0.1698
Data Index: 6253091 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0600. Min Range: -1.0600
Max Act: 0.9731. Min Act: -0.1698
Data Index: 2160833 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0600. Min Range: -1.0600
Max Act: 0.9558. Min Act: -0.1691
Data Index: 928381 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0600. Min Range: -1.0600
Max Act: 0.9472. Min Act: -0.1700
Data Index: 3455997 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0600. Min Range: -1.0600
Max Act: 0.9472. Min Act: -0.1700
Data Index: 6052487 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0600. Min Range: -1.0600
Max Act: 0.9386. Min Act: -0.1671
Data Index: 6472078 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0600. Min Range: -1.0600
Max Act: 0.9214. Min Act: -0.1700
Data Index: 7007595 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0600. Min Range: -1.0600
Max Act: 0.9214. Min Act: -0.1700
Data Index: 488886 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0600. Min Range: -1.0600
Max Act: 0.9214. Min Act: -0.1697
Data Index: 2036200 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0600. Min Range: -1.0600
Max Act: 0.9214. Min Act: -0.1700
Data Index: 8524971 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0600. Min Range: -1.0600
Max Act: 0.9042. Min Act: -0.1695
Data Index: 7991904 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0600. Min Range: -1.0600
Max Act: 0.8871. Min Act: -0.1649
Data Index: 5496504 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0600. Min Range: -1.0600
Max Act: 0.8957. Min Act: -0.1697
Data Index: 5072332 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0600. Min Range: -1.0600
Max Act: 0.8957. Min Act: -0.1698
Data Index: 6220167 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0600. Min Range: -1.0600
Max Act: 0.8786. Min Act: -0.1700
Data Index: 5748519 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19