Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 628 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4708. Min Range: -2.4708
Max Act: 2.4708. Min Act: -0.1700
Data Index: 3963687 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4708. Min Range: -2.4708
Max Act: 2.3894. Min Act: -0.1700
Data Index: 1162351 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4708. Min Range: -2.4708
Max Act: 2.3403. Min Act: -0.1700
Data Index: 468177 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4708. Min Range: -2.4708
Max Act: 2.2745. Min Act: -0.1700
Data Index: 7157571 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4708. Min Range: -2.4708
Max Act: 2.2745. Min Act: -0.1700
Data Index: 7443187 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4708. Min Range: -2.4708
Max Act: 2.2580. Min Act: -0.1700
Data Index: 7181424 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4708. Min Range: -2.4708
Max Act: 2.2745. Min Act: -0.1700
Data Index: 6569547 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4708. Min Range: -2.4708
Max Act: 2.2745. Min Act: -0.1700
Data Index: 7572385 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4708. Min Range: -2.4708
Max Act: 2.2415. Min Act: -0.1700
Data Index: 2648975 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4708. Min Range: -2.4708
Max Act: 2.2415. Min Act: -0.1700
Data Index: 6408118 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4708. Min Range: -2.4708
Max Act: 2.2580. Min Act: -0.1700
Data Index: 6042440 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4708. Min Range: -2.4708
Max Act: 2.2249. Min Act: -0.1700
Data Index: 8135463 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4708. Min Range: -2.4708
Max Act: 2.2084. Min Act: -0.1700
Data Index: 1163870 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4708. Min Range: -2.4708
Max Act: 2.2084. Min Act: -0.1700
Data Index: 351118 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4708. Min Range: -2.4708
Max Act: 2.2084. Min Act: -0.1700
Data Index: 1706819 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4708. Min Range: -2.4708
Max Act: 2.2249. Min Act: -0.1700
Data Index: 4459658 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4708. Min Range: -2.4708
Max Act: 2.2084. Min Act: -0.1700
Data Index: 3815669 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4708. Min Range: -2.4708
Max Act: 2.1918. Min Act: -0.1700
Data Index: 1015084 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4708. Min Range: -2.4708
Max Act: 2.2084. Min Act: -0.1700
Data Index: 359744 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4708. Min Range: -2.4708
Max Act: 2.2084. Min Act: -0.1700
Data Index: 1077644 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19