Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2709 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3446. Min Range: -4.3446
Max Act: 4.3446. Min Act: -0.1699
Data Index: 7898220 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3446. Min Range: -4.3446
Max Act: 4.2821. Min Act: -0.1700
Data Index: 1322635 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3446. Min Range: -4.3446
Max Act: 4.1258. Min Act: -0.1700
Data Index: 8354221 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3446. Min Range: -4.3446
Max Act: 4.0320. Min Act: -0.1700
Data Index: 2274887 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3446. Min Range: -4.3446
Max Act: 4.0320. Min Act: -0.1700
Data Index: 6286770 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3446. Min Range: -4.3446
Max Act: 3.9695. Min Act: -0.1700
Data Index: 5128500 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3446. Min Range: -4.3446
Max Act: 3.9695. Min Act: -0.1700
Data Index: 4727047 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3446. Min Range: -4.3446
Max Act: 4.0008. Min Act: -0.1700
Data Index: 4493629 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3446. Min Range: -4.3446
Max Act: 4.0008. Min Act: -0.1700
Data Index: 3749063 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3446. Min Range: -4.3446
Max Act: 4.0008. Min Act: -0.1700
Data Index: 3735959 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3446. Min Range: -4.3446
Max Act: 4.0008. Min Act: -0.1700
Data Index: 765550 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3446. Min Range: -4.3446
Max Act: 3.9695. Min Act: -0.1700
Data Index: 1675358 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3446. Min Range: -4.3446
Max Act: 4.0008. Min Act: -0.1700
Data Index: 5136075 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3446. Min Range: -4.3446
Max Act: 4.0008. Min Act: -0.1700
Data Index: 8150766 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3446. Min Range: -4.3446
Max Act: 3.9695. Min Act: -0.1700
Data Index: 6957485 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3446. Min Range: -4.3446
Max Act: 3.9695. Min Act: -0.1700
Data Index: 7455559 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3446. Min Range: -4.3446
Max Act: 3.9695. Min Act: -0.1700
Data Index: 3421798 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3446. Min Range: -4.3446
Max Act: 3.9382. Min Act: -0.1700
Data Index: 1790316 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3446. Min Range: -4.3446
Max Act: 3.9382. Min Act: -0.1700
Data Index: 3268743 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3446. Min Range: -4.3446
Max Act: 3.9695. Min Act: -0.1694
Data Index: 419198 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19