Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2745 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9322. Min Range: -6.9322
Max Act: 6.9322. Min Act: -0.1700
Data Index: 8106819 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9322. Min Range: -6.9322
Max Act: 6.8697. Min Act: -0.1700
Data Index: 2899098 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9322. Min Range: -6.9322
Max Act: 6.8072. Min Act: -0.1699
Data Index: 7831480 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9322. Min Range: -6.9322
Max Act: 6.7759. Min Act: -0.1700
Data Index: 1327942 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9322. Min Range: -6.9322
Max Act: 6.7134. Min Act: -0.1699
Data Index: 7586383 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9322. Min Range: -6.9322
Max Act: 6.7134. Min Act: -0.1700
Data Index: 5113669 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9322. Min Range: -6.9322
Max Act: 6.6822. Min Act: -0.1700
Data Index: 6235416 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9322. Min Range: -6.9322
Max Act: 6.6822. Min Act: -0.1700
Data Index: 7811972 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9322. Min Range: -6.9322
Max Act: 6.6822. Min Act: -0.1700
Data Index: 530138 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9322. Min Range: -6.9322
Max Act: 6.6822. Min Act: -0.1700
Data Index: 1729217 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9322. Min Range: -6.9322
Max Act: 6.6822. Min Act: -0.1700
Data Index: 4023222 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9322. Min Range: -6.9322
Max Act: 6.6197. Min Act: -0.1700
Data Index: 7880841 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9322. Min Range: -6.9322
Max Act: 6.6509. Min Act: -0.1700
Data Index: 3373794 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9322. Min Range: -6.9322
Max Act: 6.6197. Min Act: -0.1700
Data Index: 1667868 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9322. Min Range: -6.9322
Max Act: 6.6197. Min Act: -0.1691
Data Index: 4045602 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9322. Min Range: -6.9322
Max Act: 6.6197. Min Act: -0.1700
Data Index: 5561322 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9322. Min Range: -6.9322
Max Act: 6.5572. Min Act: -0.1700
Data Index: 7134926 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9322. Min Range: -6.9322
Max Act: 6.5884. Min Act: -0.1700
Data Index: 1854372 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9322. Min Range: -6.9322
Max Act: 6.5884. Min Act: -0.1700
Data Index: 6926956 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9322. Min Range: -6.9322
Max Act: 6.5884. Min Act: -0.1700
Data Index: 1559120 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19