Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4666 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4665. Min Range: -5.4665
Max Act: 5.4665. Min Act: -0.1700
Data Index: 1814420 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4665. Min Range: -5.4665
Max Act: 5.4353. Min Act: -0.1700
Data Index: 7998151 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4665. Min Range: -5.4665
Max Act: 5.4040. Min Act: -0.1700
Data Index: 5961164 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4665. Min Range: -5.4665
Max Act: 5.3728. Min Act: -0.1700
Data Index: 416079 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4665. Min Range: -5.4665
Max Act: 5.3415. Min Act: -0.1700
Data Index: 2297155 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4665. Min Range: -5.4665
Max Act: 5.3103. Min Act: -0.1700
Data Index: 7708167 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4665. Min Range: -5.4665
Max Act: 5.3103. Min Act: -0.1700
Data Index: 4638466 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4665. Min Range: -5.4665
Max Act: 5.3103. Min Act: -0.1700
Data Index: 55017 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4665. Min Range: -5.4665
Max Act: 5.3103. Min Act: -0.1700
Data Index: 4430801 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4665. Min Range: -5.4665
Max Act: 5.3103. Min Act: -0.1700
Data Index: 3882599 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4665. Min Range: -5.4665
Max Act: 5.3103. Min Act: -0.1700
Data Index: 3470982 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4665. Min Range: -5.4665
Max Act: 5.3103. Min Act: -0.1700
Data Index: 1534376 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4665. Min Range: -5.4665
Max Act: 5.2790. Min Act: -0.1700
Data Index: 1678953 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4665. Min Range: -5.4665
Max Act: 5.2790. Min Act: -0.1700
Data Index: 5160897 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4665. Min Range: -5.4665
Max Act: 5.2790. Min Act: -0.1700
Data Index: 2885466 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4665. Min Range: -5.4665
Max Act: 5.2790. Min Act: -0.1700
Data Index: 7004347 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4665. Min Range: -5.4665
Max Act: 5.2478. Min Act: -0.1700
Data Index: 2398796 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4665. Min Range: -5.4665
Max Act: 5.2478. Min Act: -0.1700
Data Index: 7382030 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4665. Min Range: -5.4665
Max Act: 5.2478. Min Act: -0.1700
Data Index: 4823184 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4665. Min Range: -5.4665
Max Act: 5.2478. Min Act: -0.1700
Data Index: 5037701 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19