Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1140 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5877. Min Range: -3.5877
Max Act: 3.5877. Min Act: -0.1700
Data Index: 6427603 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5877. Min Range: -3.5877
Max Act: 3.4624. Min Act: -0.1700
Data Index: 6427597 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5877. Min Range: -3.5877
Max Act: 3.3526. Min Act: -0.1700
Data Index: 6427605 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5877. Min Range: -3.5877
Max Act: 3.3369. Min Act: -0.1700
Data Index: 6427602 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5877. Min Range: -3.5877
Max Act: 3.2270. Min Act: -0.1700
Data Index: 6427600 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5877. Min Range: -3.5877
Max Act: 3.1798. Min Act: -0.1700
Data Index: 6427604 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5877. Min Range: -3.5877
Max Act: 3.1641. Min Act: -0.1700
Data Index: 1871169 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5877. Min Range: -3.5877
Max Act: 3.1484. Min Act: -0.1700
Data Index: 2948139 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5877. Min Range: -3.5877
Max Act: 3.1169. Min Act: -0.1700
Data Index: 6844769 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5877. Min Range: -3.5877
Max Act: 3.0696. Min Act: -0.1700
Data Index: 5613864 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5877. Min Range: -3.5877
Max Act: 3.0538. Min Act: -0.1700
Data Index: 2686583 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5877. Min Range: -3.5877
Max Act: 3.0696. Min Act: -0.1700
Data Index: 6427601 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5877. Min Range: -3.5877
Max Act: 3.0696. Min Act: -0.1700
Data Index: 2431521 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5877. Min Range: -3.5877
Max Act: 3.0538. Min Act: -0.1700
Data Index: 4761816 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5877. Min Range: -3.5877
Max Act: 3.0222. Min Act: -0.1700
Data Index: 4227991 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5877. Min Range: -3.5877
Max Act: 3.0222. Min Act: -0.1700
Data Index: 530534 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5877. Min Range: -3.5877
Max Act: 2.9906. Min Act: -0.1700
Data Index: 2514295 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5877. Min Range: -3.5877
Max Act: 2.9748. Min Act: -0.1700
Data Index: 4417733 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5877. Min Range: -3.5877
Max Act: 2.9590. Min Act: -0.1700
Data Index: 957331 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5877. Min Range: -3.5877
Max Act: 2.9590. Min Act: -0.1700
Data Index: 2228609 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19