Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3676 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.0787. Min Range: -0.0787
Max Act: 0.0787. Min Act: -0.1689
Data Index: 6541444 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0787. Min Range: -0.0787
Max Act: 0.0692. Min Act: -0.1700
Data Index: 3913113 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0787. Min Range: -0.0787
Max Act: 0.0509. Min Act: -0.1694
Data Index: 5044687 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0787. Min Range: -0.0787
Max Act: 0.0509. Min Act: -0.1700
Data Index: 7124303 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0787. Min Range: -0.0787
Max Act: 0.0420. Min Act: -0.1699
Data Index: 2645966 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0787. Min Range: -0.0787
Max Act: 0.0376. Min Act: -0.1699
Data Index: 8151993 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0787. Min Range: -0.0787
Max Act: 0.0333. Min Act: -0.1680
Data Index: 2624995 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0787. Min Range: -0.0787
Max Act: 0.0333. Min Act: -0.1685
Data Index: 4244428 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0787. Min Range: -0.0787
Max Act: 0.0333. Min Act: -0.1700
Data Index: 210223 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0787. Min Range: -0.0787
Max Act: 0.0248. Min Act: -0.1699
Data Index: 3331779 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0787. Min Range: -0.0787
Max Act: 0.0290. Min Act: -0.1671
Data Index: 2745031 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0787. Min Range: -0.0787
Max Act: 0.0248. Min Act: -0.1700
Data Index: 4950713 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0787. Min Range: -0.0787
Max Act: 0.0248. Min Act: -0.1700
Data Index: 2856499 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0787. Min Range: -0.0787
Max Act: 0.0248. Min Act: -0.1700
Data Index: 4458935 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0787. Min Range: -0.0787
Max Act: 0.0248. Min Act: -0.1680
Data Index: 8450203 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0787. Min Range: -0.0787
Max Act: 0.0206. Min Act: -0.1700
Data Index: 2091695 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0787. Min Range: -0.0787
Max Act: 0.0165. Min Act: -0.1694
Data Index: 3475507 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0787. Min Range: -0.0787
Max Act: 0.0165. Min Act: -0.1682
Data Index: 2181440 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0787. Min Range: -0.0787
Max Act: 0.0165. Min Act: -0.1679
Data Index: 3955324 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0787. Min Range: -0.0787
Max Act: 0.0206. Min Act: -0.1700
Data Index: 4863156 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19