Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3551 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6507. Min Range: -2.6507
Max Act: 2.6507. Min Act: -0.1694
Data Index: 8198902 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6507. Min Range: -2.6507
Max Act: 2.5864. Min Act: -0.1700
Data Index: 1124436 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6507. Min Range: -2.6507
Max Act: 2.5380. Min Act: -0.1698
Data Index: 5711471 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6507. Min Range: -2.6507
Max Act: 2.5056. Min Act: -0.1699
Data Index: 3311487 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6507. Min Range: -2.6507
Max Act: 2.4894. Min Act: -0.1698
Data Index: 3590137 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6507. Min Range: -2.6507
Max Act: 2.4732. Min Act: -0.1695
Data Index: 2716265 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6507. Min Range: -2.6507
Max Act: 2.4732. Min Act: -0.1699
Data Index: 3873888 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6507. Min Range: -2.6507
Max Act: 2.4732. Min Act: -0.1700
Data Index: 1892855 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6507. Min Range: -2.6507
Max Act: 2.4894. Min Act: -0.1698
Data Index: 5245079 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6507. Min Range: -2.6507
Max Act: 2.4732. Min Act: -0.1674
Data Index: 2906816 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6507. Min Range: -2.6507
Max Act: 2.4570. Min Act: -0.1696
Data Index: 361208 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6507. Min Range: -2.6507
Max Act: 2.4570. Min Act: -0.1693
Data Index: 7132604 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6507. Min Range: -2.6507
Max Act: 2.4570. Min Act: -0.1683
Data Index: 5279423 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6507. Min Range: -2.6507
Max Act: 2.4244. Min Act: -0.1697
Data Index: 802248 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6507. Min Range: -2.6507
Max Act: 2.4570. Min Act: -0.1699
Data Index: 4385098 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6507. Min Range: -2.6507
Max Act: 2.4570. Min Act: -0.1699
Data Index: 4674916 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6507. Min Range: -2.6507
Max Act: 2.4407. Min Act: -0.1700
Data Index: 1573224 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6507. Min Range: -2.6507
Max Act: 2.4081. Min Act: -0.1700
Data Index: 4042524 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6507. Min Range: -2.6507
Max Act: 2.4570. Min Act: -0.1700
Data Index: 2778297 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6507. Min Range: -2.6507
Max Act: 2.4407. Min Act: -0.1700
Data Index: 3388290 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19