Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 758 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2168. Min Range: -7.2168
Max Act: 7.2168. Min Act: -0.1700
Data Index: 8536906 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2168. Min Range: -7.2168
Max Act: 6.8418. Min Act: -0.1700
Data Index: 2827375 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2168. Min Range: -7.2168
Max Act: 6.8418. Min Act: -0.1700
Data Index: 700978 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2168. Min Range: -7.2168
Max Act: 6.8105. Min Act: -0.1700
Data Index: 6114390 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2168. Min Range: -7.2168
Max Act: 6.7793. Min Act: -0.1700
Data Index: 2382003 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2168. Min Range: -7.2168
Max Act: 6.7793. Min Act: -0.1700
Data Index: 2670401 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2168. Min Range: -7.2168
Max Act: 6.7793. Min Act: -0.1700
Data Index: 1746730 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2168. Min Range: -7.2168
Max Act: 6.7793. Min Act: -0.1700
Data Index: 5576845 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2168. Min Range: -7.2168
Max Act: 6.7793. Min Act: -0.1700
Data Index: 4649797 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2168. Min Range: -7.2168
Max Act: 6.7480. Min Act: -0.1700
Data Index: 7581372 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2168. Min Range: -7.2168
Max Act: 6.7480. Min Act: -0.1700
Data Index: 1152985 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2168. Min Range: -7.2168
Max Act: 6.7168. Min Act: -0.1700
Data Index: 2057067 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2168. Min Range: -7.2168
Max Act: 6.6855. Min Act: -0.1700
Data Index: 914077 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2168. Min Range: -7.2168
Max Act: 6.6855. Min Act: -0.1700
Data Index: 7663316 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2168. Min Range: -7.2168
Max Act: 6.7168. Min Act: -0.1700
Data Index: 5925401 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2168. Min Range: -7.2168
Max Act: 6.6855. Min Act: -0.1700
Data Index: 2343616 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2168. Min Range: -7.2168
Max Act: 6.6543. Min Act: -0.1700
Data Index: 5465533 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2168. Min Range: -7.2168
Max Act: 6.6855. Min Act: -0.1700
Data Index: 3065176 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2168. Min Range: -7.2168
Max Act: 6.6855. Min Act: -0.1700
Data Index: 25611 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2168. Min Range: -7.2168
Max Act: 6.6855. Min Act: -0.1700
Data Index: 3580101 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19