Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5484 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7109. Min Range: -4.7109
Max Act: 4.7109. Min Act: -0.1700
Data Index: 8647283 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7109. Min Range: -4.7109
Max Act: 4.6797. Min Act: -0.1700
Data Index: 8183115 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7109. Min Range: -4.7109
Max Act: 4.6172. Min Act: -0.1700
Data Index: 93786 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7109. Min Range: -4.7109
Max Act: 4.5234. Min Act: -0.1700
Data Index: 1532246 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7109. Min Range: -4.7109
Max Act: 4.4922. Min Act: -0.1700
Data Index: 5779970 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7109. Min Range: -4.7109
Max Act: 4.4609. Min Act: -0.1700
Data Index: 7861352 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7109. Min Range: -4.7109
Max Act: 4.4297. Min Act: -0.1700
Data Index: 6531325 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7109. Min Range: -4.7109
Max Act: 4.3984. Min Act: -0.1700
Data Index: 845296 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7109. Min Range: -4.7109
Max Act: 4.4297. Min Act: -0.1700
Data Index: 8079238 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7109. Min Range: -4.7109
Max Act: 4.3984. Min Act: -0.1700
Data Index: 6743628 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7109. Min Range: -4.7109
Max Act: 4.3984. Min Act: -0.1700
Data Index: 1566189 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7109. Min Range: -4.7109
Max Act: 4.3984. Min Act: -0.1700
Data Index: 3821275 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7109. Min Range: -4.7109
Max Act: 4.3672. Min Act: -0.1700
Data Index: 2518237 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7109. Min Range: -4.7109
Max Act: 4.3672. Min Act: -0.1700
Data Index: 682590 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7109. Min Range: -4.7109
Max Act: 4.3672. Min Act: -0.1700
Data Index: 4183726 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7109. Min Range: -4.7109
Max Act: 4.3672. Min Act: -0.1700
Data Index: 871946 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7109. Min Range: -4.7109
Max Act: 4.3359. Min Act: -0.1700
Data Index: 8381142 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7109. Min Range: -4.7109
Max Act: 4.3672. Min Act: -0.1700
Data Index: 5861342 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7109. Min Range: -4.7109
Max Act: 4.3359. Min Act: -0.1700
Data Index: 6455762 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7109. Min Range: -4.7109
Max Act: 4.3359. Min Act: -0.1700
Data Index: 7020118 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19