Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3111 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2134. Min Range: -8.2134
Max Act: 8.2134. Min Act: -0.1700
Data Index: 6646354 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2134. Min Range: -8.2134
Max Act: 8.2134. Min Act: -0.1700
Data Index: 715270 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2134. Min Range: -8.2134
Max Act: 8.0259. Min Act: -0.1700
Data Index: 168 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2134. Min Range: -8.2134
Max Act: 7.9634. Min Act: -0.1700
Data Index: 6138543 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2134. Min Range: -8.2134
Max Act: 7.9634. Min Act: -0.1700
Data Index: 1364814 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2134. Min Range: -8.2134
Max Act: 7.9009. Min Act: -0.1700
Data Index: 8248627 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2134. Min Range: -8.2134
Max Act: 7.8384. Min Act: -0.1700
Data Index: 291866 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2134. Min Range: -8.2134
Max Act: 7.8384. Min Act: -0.1700
Data Index: 1153694 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2134. Min Range: -8.2134
Max Act: 7.8384. Min Act: -0.1700
Data Index: 1258299 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2134. Min Range: -8.2134
Max Act: 7.8384. Min Act: -0.1700
Data Index: 646265 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2134. Min Range: -8.2134
Max Act: 7.8384. Min Act: -0.1700
Data Index: 607917 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2134. Min Range: -8.2134
Max Act: 7.8384. Min Act: -0.1700
Data Index: 880001 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2134. Min Range: -8.2134
Max Act: 7.8384. Min Act: -0.1700
Data Index: 1234124 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2134. Min Range: -8.2134
Max Act: 7.8384. Min Act: -0.1700
Data Index: 583018 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2134. Min Range: -8.2134
Max Act: 7.8384. Min Act: -0.1700
Data Index: 1292291 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2134. Min Range: -8.2134
Max Act: 7.8384. Min Act: -0.1700
Data Index: 1532977 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2134. Min Range: -8.2134
Max Act: 7.8384. Min Act: -0.1700
Data Index: 1514574 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2134. Min Range: -8.2134
Max Act: 7.8384. Min Act: -0.1700
Data Index: 553763 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2134. Min Range: -8.2134
Max Act: 7.8384. Min Act: -0.1700
Data Index: 1133870 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2134. Min Range: -8.2134
Max Act: 7.8384. Min Act: -0.1700
Data Index: 1132238 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19