Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2396 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0753. Min Range: -6.0753
Max Act: 6.0753. Min Act: -0.1700
Data Index: 1915826 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0753. Min Range: -6.0753
Max Act: 6.0441. Min Act: -0.1700
Data Index: 6532581 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0753. Min Range: -6.0753
Max Act: 5.9503. Min Act: -0.1700
Data Index: 2679676 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0753. Min Range: -6.0753
Max Act: 5.9191. Min Act: -0.1700
Data Index: 7409286 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0753. Min Range: -6.0753
Max Act: 5.7941. Min Act: -0.1700
Data Index: 415935 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0753. Min Range: -6.0753
Max Act: 5.7941. Min Act: -0.1700
Data Index: 5142343 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0753. Min Range: -6.0753
Max Act: 5.7628. Min Act: -0.1700
Data Index: 2076262 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0753. Min Range: -6.0753
Max Act: 5.7628. Min Act: -0.1700
Data Index: 4667637 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0753. Min Range: -6.0753
Max Act: 5.6691. Min Act: -0.1700
Data Index: 8309001 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0753. Min Range: -6.0753
Max Act: 5.6691. Min Act: -0.1700
Data Index: 8805222 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0753. Min Range: -6.0753
Max Act: 5.6378. Min Act: -0.1700
Data Index: 4428348 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0753. Min Range: -6.0753
Max Act: 5.6378. Min Act: -0.1700
Data Index: 1456159 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0753. Min Range: -6.0753
Max Act: 5.5753. Min Act: -0.1700
Data Index: 7130937 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0753. Min Range: -6.0753
Max Act: 5.5753. Min Act: -0.1700
Data Index: 6545410 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0753. Min Range: -6.0753
Max Act: 5.5753. Min Act: -0.1700
Data Index: 6532582 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0753. Min Range: -6.0753
Max Act: 5.5441. Min Act: -0.1700
Data Index: 997883 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0753. Min Range: -6.0753
Max Act: 5.5128. Min Act: -0.1700
Data Index: 6728334 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0753. Min Range: -6.0753
Max Act: 5.5128. Min Act: -0.1700
Data Index: 1163202 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0753. Min Range: -6.0753
Max Act: 5.5441. Min Act: -0.1700
Data Index: 2689748 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0753. Min Range: -6.0753
Max Act: 5.5441. Min Act: -0.1700
Data Index: 6958058 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19