Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3248 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4672. Min Range: -5.4672
Max Act: 5.4672. Min Act: -0.1700
Data Index: 6006595 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4672. Min Range: -5.4672
Max Act: 5.2172. Min Act: -0.1700
Data Index: 2022982 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4672. Min Range: -5.4672
Max Act: 5.1234. Min Act: -0.1700
Data Index: 8697415 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4672. Min Range: -5.4672
Max Act: 5.1547. Min Act: -0.1700
Data Index: 4835884 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4672. Min Range: -5.4672
Max Act: 5.0609. Min Act: -0.1700
Data Index: 6521629 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4672. Min Range: -5.4672
Max Act: 5.0609. Min Act: -0.1700
Data Index: 6252488 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4672. Min Range: -5.4672
Max Act: 4.9984. Min Act: -0.1700
Data Index: 8530194 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4672. Min Range: -5.4672
Max Act: 4.9984. Min Act: -0.1700
Data Index: 3545624 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4672. Min Range: -5.4672
Max Act: 4.9984. Min Act: -0.1700
Data Index: 471435 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4672. Min Range: -5.4672
Max Act: 4.9672. Min Act: -0.1700
Data Index: 2732889 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4672. Min Range: -5.4672
Max Act: 4.9359. Min Act: -0.1700
Data Index: 718681 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4672. Min Range: -5.4672
Max Act: 4.9047. Min Act: -0.1700
Data Index: 6222662 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4672. Min Range: -5.4672
Max Act: 4.9047. Min Act: -0.1700
Data Index: 1745905 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4672. Min Range: -5.4672
Max Act: 4.9047. Min Act: -0.1700
Data Index: 1023713 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4672. Min Range: -5.4672
Max Act: 4.8734. Min Act: -0.1700
Data Index: 6166459 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4672. Min Range: -5.4672
Max Act: 4.8734. Min Act: -0.1700
Data Index: 2033682 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4672. Min Range: -5.4672
Max Act: 4.8734. Min Act: -0.1700
Data Index: 4072510 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4672. Min Range: -5.4672
Max Act: 4.8734. Min Act: -0.1700
Data Index: 7954404 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4672. Min Range: -5.4672
Max Act: 4.8422. Min Act: -0.1700
Data Index: 4457363 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4672. Min Range: -5.4672
Max Act: 4.8422. Min Act: -0.1700
Data Index: 7028981 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19