Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5607 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9970. Min Range: -4.9970
Max Act: 4.9970. Min Act: -0.1700
Data Index: 8776026 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9970. Min Range: -4.9970
Max Act: 4.9345. Min Act: -0.1699
Data Index: 7790843 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9970. Min Range: -4.9970
Max Act: 4.8095. Min Act: -0.1697
Data Index: 4825607 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9970. Min Range: -4.9970
Max Act: 4.8407. Min Act: -0.1700
Data Index: 6912879 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9970. Min Range: -4.9970
Max Act: 4.8720. Min Act: -0.1700
Data Index: 925816 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9970. Min Range: -4.9970
Max Act: 4.7782. Min Act: -0.1700
Data Index: 5219334 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9970. Min Range: -4.9970
Max Act: 4.8095. Min Act: -0.1700
Data Index: 1762017 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9970. Min Range: -4.9970
Max Act: 4.7782. Min Act: -0.1700
Data Index: 532179 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9970. Min Range: -4.9970
Max Act: 4.7782. Min Act: -0.1700
Data Index: 5219333 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9970. Min Range: -4.9970
Max Act: 4.7782. Min Act: -0.1700
Data Index: 1198082 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9970. Min Range: -4.9970
Max Act: 4.7782. Min Act: -0.1700
Data Index: 7349933 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9970. Min Range: -4.9970
Max Act: 4.7470. Min Act: -0.1700
Data Index: 211811 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9970. Min Range: -4.9970
Max Act: 4.7470. Min Act: -0.1700
Data Index: 762301 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9970. Min Range: -4.9970
Max Act: 4.7782. Min Act: -0.1700
Data Index: 5219347 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9970. Min Range: -4.9970
Max Act: 4.7470. Min Act: -0.1700
Data Index: 3396537 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9970. Min Range: -4.9970
Max Act: 4.7157. Min Act: -0.1700
Data Index: 1981823 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9970. Min Range: -4.9970
Max Act: 4.7157. Min Act: -0.1700
Data Index: 1123229 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9970. Min Range: -4.9970
Max Act: 4.6845. Min Act: -0.1700
Data Index: 1806252 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9970. Min Range: -4.9970
Max Act: 4.7157. Min Act: -0.1700
Data Index: 5206330 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9970. Min Range: -4.9970
Max Act: 4.7157. Min Act: -0.1700
Data Index: 237457 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19