Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2968 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9157. Min Range: -7.9157
Max Act: 7.9157. Min Act: -0.1700
Data Index: 5469926 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9157. Min Range: -7.9157
Max Act: 7.6032. Min Act: -0.1700
Data Index: 4287638 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9157. Min Range: -7.9157
Max Act: 7.3532. Min Act: -0.1700
Data Index: 6776307 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9157. Min Range: -7.9157
Max Act: 7.1032. Min Act: -0.1700
Data Index: 6979935 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9157. Min Range: -7.9157
Max Act: 7.0094. Min Act: -0.1700
Data Index: 6098346 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9157. Min Range: -7.9157
Max Act: 6.9469. Min Act: -0.1700
Data Index: 7968047 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9157. Min Range: -7.9157
Max Act: 6.9469. Min Act: -0.1700
Data Index: 7440236 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9157. Min Range: -7.9157
Max Act: 6.9469. Min Act: -0.1700
Data Index: 615501 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9157. Min Range: -7.9157
Max Act: 6.9469. Min Act: -0.1700
Data Index: 6679876 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9157. Min Range: -7.9157
Max Act: 6.9469. Min Act: -0.1700
Data Index: 4835833 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9157. Min Range: -7.9157
Max Act: 6.9157. Min Act: -0.1700
Data Index: 5619569 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9157. Min Range: -7.9157
Max Act: 6.9157. Min Act: -0.1700
Data Index: 1734306 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9157. Min Range: -7.9157
Max Act: 6.9157. Min Act: -0.1700
Data Index: 1480273 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9157. Min Range: -7.9157
Max Act: 6.9157. Min Act: -0.1700
Data Index: 1308901 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9157. Min Range: -7.9157
Max Act: 6.8844. Min Act: -0.1700
Data Index: 2862440 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9157. Min Range: -7.9157
Max Act: 6.8844. Min Act: -0.1700
Data Index: 15758 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9157. Min Range: -7.9157
Max Act: 6.8844. Min Act: -0.1700
Data Index: 7342607 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9157. Min Range: -7.9157
Max Act: 6.9157. Min Act: -0.1700
Data Index: 7102877 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9157. Min Range: -7.9157
Max Act: 6.8219. Min Act: -0.1700
Data Index: 6976338 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9157. Min Range: -7.9157
Max Act: 6.8532. Min Act: -0.1700
Data Index: 5188083 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19