Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2889 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5268. Min Range: -5.5268
Max Act: 5.5268. Min Act: -0.1700
Data Index: 8267572 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5268. Min Range: -5.5268
Max Act: 5.4331. Min Act: -0.1700
Data Index: 7871550 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5268. Min Range: -5.5268
Max Act: 5.3393. Min Act: -0.1700
Data Index: 2962938 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5268. Min Range: -5.5268
Max Act: 5.2456. Min Act: -0.1700
Data Index: 6441001 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5268. Min Range: -5.5268
Max Act: 5.2143. Min Act: -0.1700
Data Index: 3336317 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5268. Min Range: -5.5268
Max Act: 5.1518. Min Act: -0.1700
Data Index: 3620404 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5268. Min Range: -5.5268
Max Act: 5.1518. Min Act: -0.1700
Data Index: 8053096 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5268. Min Range: -5.5268
Max Act: 5.1518. Min Act: -0.1700
Data Index: 6925826 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5268. Min Range: -5.5268
Max Act: 5.1206. Min Act: -0.1700
Data Index: 6925825 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5268. Min Range: -5.5268
Max Act: 5.0893. Min Act: -0.1699
Data Index: 2527671 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5268. Min Range: -5.5268
Max Act: 5.0581. Min Act: -0.1700
Data Index: 6804492 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5268. Min Range: -5.5268
Max Act: 5.0893. Min Act: -0.1700
Data Index: 2223742 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5268. Min Range: -5.5268
Max Act: 5.0581. Min Act: -0.1700
Data Index: 2962937 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5268. Min Range: -5.5268
Max Act: 5.0581. Min Act: -0.1700
Data Index: 1383611 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5268. Min Range: -5.5268
Max Act: 5.0268. Min Act: -0.1700
Data Index: 3014413 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5268. Min Range: -5.5268
Max Act: 5.0268. Min Act: -0.1700
Data Index: 6925833 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5268. Min Range: -5.5268
Max Act: 5.0268. Min Act: -0.1700
Data Index: 2372162 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5268. Min Range: -5.5268
Max Act: 4.9956. Min Act: -0.1700
Data Index: 515441 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5268. Min Range: -5.5268
Max Act: 5.0268. Min Act: -0.1700
Data Index: 1737223 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5268. Min Range: -5.5268
Max Act: 4.9956. Min Act: -0.1700
Data Index: 2386607 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19