Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3291 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4273. Min Range: -3.4273
Max Act: 3.4273. Min Act: -0.1700
Data Index: 3977037 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4273. Min Range: -3.4273
Max Act: 3.3646. Min Act: -0.1700
Data Index: 4148044 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4273. Min Range: -3.4273
Max Act: 3.2861. Min Act: -0.1700
Data Index: 5842942 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4273. Min Range: -3.4273
Max Act: 3.3018. Min Act: -0.1700
Data Index: 1354364 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4273. Min Range: -3.4273
Max Act: 3.2861. Min Act: -0.1700
Data Index: 1949820 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4273. Min Range: -3.4273
Max Act: 3.2547. Min Act: -0.1700
Data Index: 1696304 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4273. Min Range: -3.4273
Max Act: 3.2704. Min Act: -0.1700
Data Index: 7573122 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4273. Min Range: -3.4273
Max Act: 3.2233. Min Act: -0.1700
Data Index: 7007381 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4273. Min Range: -3.4273
Max Act: 3.2076. Min Act: -0.1700
Data Index: 99922 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4273. Min Range: -3.4273
Max Act: 3.2233. Min Act: -0.1700
Data Index: 5918729 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4273. Min Range: -3.4273
Max Act: 3.2076. Min Act: -0.1700
Data Index: 7072144 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4273. Min Range: -3.4273
Max Act: 3.1761. Min Act: -0.1700
Data Index: 1728106 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4273. Min Range: -3.4273
Max Act: 3.1604. Min Act: -0.1700
Data Index: 1458291 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4273. Min Range: -3.4273
Max Act: 3.1761. Min Act: -0.1700
Data Index: 7976425 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4273. Min Range: -3.4273
Max Act: 3.1761. Min Act: -0.1700
Data Index: 135593 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4273. Min Range: -3.4273
Max Act: 3.1761. Min Act: -0.1700
Data Index: 6395616 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4273. Min Range: -3.4273
Max Act: 3.1446. Min Act: -0.1700
Data Index: 6601601 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4273. Min Range: -3.4273
Max Act: 3.1604. Min Act: -0.1700
Data Index: 1534763 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4273. Min Range: -3.4273
Max Act: 3.1604. Min Act: -0.1700
Data Index: 6850360 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4273. Min Range: -3.4273
Max Act: 3.1604. Min Act: -0.1700
Data Index: 2358151 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19