Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4540 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2041. Min Range: -4.2041
Max Act: 4.2041. Min Act: -0.1700
Data Index: 7272836 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2041. Min Range: -4.2041
Max Act: 4.0791. Min Act: -0.1700
Data Index: 6845131 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2041. Min Range: -4.2041
Max Act: 4.0478. Min Act: -0.1700
Data Index: 3972847 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2041. Min Range: -4.2041
Max Act: 4.0478. Min Act: -0.1700
Data Index: 2570608 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2041. Min Range: -4.2041
Max Act: 4.0478. Min Act: -0.1700
Data Index: 950299 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2041. Min Range: -4.2041
Max Act: 4.0166. Min Act: -0.1700
Data Index: 5649981 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2041. Min Range: -4.2041
Max Act: 4.0478. Min Act: -0.1700
Data Index: 4043349 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2041. Min Range: -4.2041
Max Act: 4.0166. Min Act: -0.1700
Data Index: 290856 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2041. Min Range: -4.2041
Max Act: 3.9853. Min Act: -0.1700
Data Index: 1106198 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2041. Min Range: -4.2041
Max Act: 4.0166. Min Act: -0.1700
Data Index: 6948793 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2041. Min Range: -4.2041
Max Act: 4.0166. Min Act: -0.1700
Data Index: 650526 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2041. Min Range: -4.2041
Max Act: 4.0166. Min Act: -0.1700
Data Index: 6864085 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2041. Min Range: -4.2041
Max Act: 4.0478. Min Act: -0.1700
Data Index: 1284893 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2041. Min Range: -4.2041
Max Act: 3.9853. Min Act: -0.1700
Data Index: 633185 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2041. Min Range: -4.2041
Max Act: 3.9853. Min Act: -0.1700
Data Index: 7329721 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2041. Min Range: -4.2041
Max Act: 3.9853. Min Act: -0.1700
Data Index: 5445674 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2041. Min Range: -4.2041
Max Act: 3.9853. Min Act: -0.1700
Data Index: 7845802 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2041. Min Range: -4.2041
Max Act: 3.9853. Min Act: -0.1700
Data Index: 2434 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2041. Min Range: -4.2041
Max Act: 3.9853. Min Act: -0.1700
Data Index: 4113897 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2041. Min Range: -4.2041
Max Act: 3.9540. Min Act: -0.1700
Data Index: 1164926 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19