Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2797 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9416. Min Range: -2.9416
Max Act: 2.9416. Min Act: -0.1700
Data Index: 955877 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9416. Min Range: -2.9416
Max Act: 2.8782. Min Act: -0.1700
Data Index: 4258450 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9416. Min Range: -2.9416
Max Act: 2.8623. Min Act: -0.1700
Data Index: 8144565 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9416. Min Range: -2.9416
Max Act: 2.8623. Min Act: -0.1700
Data Index: 6532668 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9416. Min Range: -2.9416
Max Act: 2.8305. Min Act: -0.1700
Data Index: 5787408 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9416. Min Range: -2.9416
Max Act: 2.8146. Min Act: -0.1700
Data Index: 495926 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9416. Min Range: -2.9416
Max Act: 2.7987. Min Act: -0.1700
Data Index: 308984 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9416. Min Range: -2.9416
Max Act: 2.7828. Min Act: -0.1700
Data Index: 6175435 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9416. Min Range: -2.9416
Max Act: 2.7668. Min Act: -0.1700
Data Index: 235200 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9416. Min Range: -2.9416
Max Act: 2.7668. Min Act: -0.1700
Data Index: 8096708 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9416. Min Range: -2.9416
Max Act: 2.7509. Min Act: -0.1700
Data Index: 1714457 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9416. Min Range: -2.9416
Max Act: 2.7349. Min Act: -0.1700
Data Index: 604952 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9416. Min Range: -2.9416
Max Act: 2.7189. Min Act: -0.1700
Data Index: 3308031 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9416. Min Range: -2.9416
Max Act: 2.7349. Min Act: -0.1700
Data Index: 2404604 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9416. Min Range: -2.9416
Max Act: 2.7349. Min Act: -0.1700
Data Index: 5302402 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9416. Min Range: -2.9416
Max Act: 2.7029. Min Act: -0.1700
Data Index: 7338860 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9416. Min Range: -2.9416
Max Act: 2.7189. Min Act: -0.1700
Data Index: 1620551 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9416. Min Range: -2.9416
Max Act: 2.7189. Min Act: -0.1700
Data Index: 725517 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9416. Min Range: -2.9416
Max Act: 2.7029. Min Act: -0.1700
Data Index: 4697341 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9416. Min Range: -2.9416
Max Act: 2.7029. Min Act: -0.1700
Data Index: 5410411 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19