Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 7 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.2919. Min Act: -0.1700
Data Index: 452032 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.1044. Min Act: -0.1700
Data Index: 2404178 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.1044. Min Act: -0.1700
Data Index: 8111768 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.1044. Min Act: -0.1700
Data Index: 287487 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.0731. Min Act: -0.1700
Data Index: 8332947 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.0731. Min Act: -0.1700
Data Index: 495996 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.0731. Min Act: -0.1700
Data Index: 1574425 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.0418. Min Act: -0.1700
Data Index: 3608034 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.0731. Min Act: -0.1700
Data Index: 2775551 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.0418. Min Act: -0.1700
Data Index: 206549 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2919. Min Range: -4.2919
Max Act: 3.9793. Min Act: -0.1700
Data Index: 862854 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.0418. Min Act: -0.1700
Data Index: 2964757 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.0418. Min Act: -0.1700
Data Index: 6988556 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.0418. Min Act: -0.1700
Data Index: 4526718 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2919. Min Range: -4.2919
Max Act: 3.9793. Min Act: -0.1700
Data Index: 8786814 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2919. Min Range: -4.2919
Max Act: 3.9793. Min Act: -0.1700
Data Index: 58807 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2919. Min Range: -4.2919
Max Act: 3.9793. Min Act: -0.1700
Data Index: 5794198 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.0106. Min Act: -0.1700
Data Index: 4525274 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2919. Min Range: -4.2919
Max Act: 3.9793. Min Act: -0.1700
Data Index: 4848167 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.0106. Min Act: -0.1700
Data Index: 3065500 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19