Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6367 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0369. Min Range: -6.0369
Max Act: 6.0369. Min Act: -0.1700
Data Index: 106148 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0369. Min Range: -6.0369
Max Act: 6.0056. Min Act: -0.1700
Data Index: 5308116 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0369. Min Range: -6.0369
Max Act: 5.9119. Min Act: -0.1700
Data Index: 4031351 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0369. Min Range: -6.0369
Max Act: 5.8181. Min Act: -0.1700
Data Index: 106151 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0369. Min Range: -6.0369
Max Act: 5.6619. Min Act: -0.1700
Data Index: 3551331 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0369. Min Range: -6.0369
Max Act: 5.6931. Min Act: -0.1700
Data Index: 1867893 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0369. Min Range: -6.0369
Max Act: 5.6306. Min Act: -0.1700
Data Index: 4787790 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0369. Min Range: -6.0369
Max Act: 5.5994. Min Act: -0.1700
Data Index: 8037721 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0369. Min Range: -6.0369
Max Act: 5.5681. Min Act: -0.1700
Data Index: 3813044 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0369. Min Range: -6.0369
Max Act: 5.5681. Min Act: -0.1700
Data Index: 4402583 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0369. Min Range: -6.0369
Max Act: 5.5369. Min Act: -0.1700
Data Index: 7555501 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0369. Min Range: -6.0369
Max Act: 5.5056. Min Act: -0.1700
Data Index: 7280248 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0369. Min Range: -6.0369
Max Act: 5.5056. Min Act: -0.1700
Data Index: 5206054 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0369. Min Range: -6.0369
Max Act: 5.5056. Min Act: -0.1700
Data Index: 3120364 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0369. Min Range: -6.0369
Max Act: 5.5056. Min Act: -0.1700
Data Index: 5146354 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0369. Min Range: -6.0369
Max Act: 5.4744. Min Act: -0.1700
Data Index: 7122108 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0369. Min Range: -6.0369
Max Act: 5.4744. Min Act: -0.1700
Data Index: 2279936 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0369. Min Range: -6.0369
Max Act: 5.4744. Min Act: -0.1700
Data Index: 8168574 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0369. Min Range: -6.0369
Max Act: 5.4744. Min Act: -0.1700
Data Index: 1907429 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0369. Min Range: -6.0369
Max Act: 5.4431. Min Act: -0.1700
Data Index: 5356067 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19