Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2736. Min Range: -5.2736
Max Act: 5.2736. Min Act: -0.1700
Data Index: 7069432 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2736. Min Range: -5.2736
Max Act: 5.2423. Min Act: -0.1700
Data Index: 267226 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2736. Min Range: -5.2736
Max Act: 5.1798. Min Act: -0.1700
Data Index: 8516486 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2736. Min Range: -5.2736
Max Act: 5.1798. Min Act: -0.1700
Data Index: 6635370 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2736. Min Range: -5.2736
Max Act: 5.1798. Min Act: -0.1700
Data Index: 2422337 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2736. Min Range: -5.2736
Max Act: 5.1486. Min Act: -0.1700
Data Index: 2256620 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2736. Min Range: -5.2736
Max Act: 5.1173. Min Act: -0.1700
Data Index: 2522113 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2736. Min Range: -5.2736
Max Act: 5.1486. Min Act: -0.1700
Data Index: 4345660 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2736. Min Range: -5.2736
Max Act: 5.0861. Min Act: -0.1700
Data Index: 3838284 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2736. Min Range: -5.2736
Max Act: 5.1486. Min Act: -0.1700
Data Index: 2467367 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2736. Min Range: -5.2736
Max Act: 5.1173. Min Act: -0.1700
Data Index: 786985 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2736. Min Range: -5.2736
Max Act: 5.0861. Min Act: -0.1700
Data Index: 6100205 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2736. Min Range: -5.2736
Max Act: 5.0861. Min Act: -0.1700
Data Index: 6690324 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2736. Min Range: -5.2736
Max Act: 5.0861. Min Act: -0.1700
Data Index: 580129 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2736. Min Range: -5.2736
Max Act: 5.0548. Min Act: -0.1700
Data Index: 4469002 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2736. Min Range: -5.2736
Max Act: 5.0861. Min Act: -0.1700
Data Index: 7049633 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2736. Min Range: -5.2736
Max Act: 5.0236. Min Act: -0.1700
Data Index: 4549356 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2736. Min Range: -5.2736
Max Act: 5.0236. Min Act: -0.1700
Data Index: 4709023 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2736. Min Range: -5.2736
Max Act: 5.0236. Min Act: -0.1700
Data Index: 1866711 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2736. Min Range: -5.2736
Max Act: 5.0236. Min Act: -0.1700
Data Index: 159728 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19