Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3076 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8199. Min Range: -3.8199
Max Act: 3.8199. Min Act: -0.1700
Data Index: 2988943 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8199. Min Range: -3.8199
Max Act: 3.7574. Min Act: -0.1700
Data Index: 7792306 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8199. Min Range: -3.8199
Max Act: 3.7574. Min Act: -0.1700
Data Index: 2678863 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8199. Min Range: -3.8199
Max Act: 3.7574. Min Act: -0.1700
Data Index: 3433752 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8199. Min Range: -3.8199
Max Act: 3.7261. Min Act: -0.1700
Data Index: 862966 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8199. Min Range: -3.8199
Max Act: 3.7104. Min Act: -0.1700
Data Index: 3038756 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8199. Min Range: -3.8199
Max Act: 3.7261. Min Act: -0.1700
Data Index: 246528 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8199. Min Range: -3.8199
Max Act: 3.7261. Min Act: -0.1700
Data Index: 4558461 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8199. Min Range: -3.8199
Max Act: 3.7261. Min Act: -0.1700
Data Index: 2762172 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8199. Min Range: -3.8199
Max Act: 3.6948. Min Act: -0.1700
Data Index: 3271073 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8199. Min Range: -3.8199
Max Act: 3.7104. Min Act: -0.1700
Data Index: 4814250 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8199. Min Range: -3.8199
Max Act: 3.7104. Min Act: -0.1700
Data Index: 4368702 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8199. Min Range: -3.8199
Max Act: 3.6948. Min Act: -0.1700
Data Index: 4119103 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8199. Min Range: -3.8199
Max Act: 3.6792. Min Act: -0.1700
Data Index: 1401705 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8199. Min Range: -3.8199
Max Act: 3.6948. Min Act: -0.1700
Data Index: 5129229 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8199. Min Range: -3.8199
Max Act: 3.6792. Min Act: -0.1700
Data Index: 7808269 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8199. Min Range: -3.8199
Max Act: 3.6792. Min Act: -0.1700
Data Index: 1766314 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8199. Min Range: -3.8199
Max Act: 3.6635. Min Act: -0.1700
Data Index: 1723572 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8199. Min Range: -3.8199
Max Act: 3.6635. Min Act: -0.1700
Data Index: 6962706 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8199. Min Range: -3.8199
Max Act: 3.6635. Min Act: -0.1700
Data Index: 4179932 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #19