Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4511 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.2446. Min Act: -0.1700
Data Index: 2126548 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.1821. Min Act: -0.1700
Data Index: 2144369 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.1509. Min Act: -0.1700
Data Index: 2713742 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.0884. Min Act: -0.1700
Data Index: 7610817 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.0259. Min Act: -0.1700
Data Index: 5970284 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.0259. Min Act: -0.1700
Data Index: 5426016 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2446. Min Range: -6.2446
Max Act: 5.9009. Min Act: -0.1700
Data Index: 8653165 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2446. Min Range: -6.2446
Max Act: 5.9009. Min Act: -0.1700
Data Index: 7633988 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2446. Min Range: -6.2446
Max Act: 5.9009. Min Act: -0.1700
Data Index: 6756806 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2446. Min Range: -6.2446
Max Act: 5.9009. Min Act: -0.1700
Data Index: 5120629 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2446. Min Range: -6.2446
Max Act: 5.8696. Min Act: -0.1700
Data Index: 4470638 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2446. Min Range: -6.2446
Max Act: 5.8696. Min Act: -0.1700
Data Index: 1883148 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2446. Min Range: -6.2446
Max Act: 5.8384. Min Act: -0.1700
Data Index: 2650437 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2446. Min Range: -6.2446
Max Act: 5.8071. Min Act: -0.1700
Data Index: 5120630 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2446. Min Range: -6.2446
Max Act: 5.8071. Min Act: -0.1700
Data Index: 2626757 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2446. Min Range: -6.2446
Max Act: 5.7759. Min Act: -0.1700
Data Index: 6108675 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2446. Min Range: -6.2446
Max Act: 5.8071. Min Act: -0.1700
Data Index: 6133746 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2446. Min Range: -6.2446
Max Act: 5.7759. Min Act: -0.1700
Data Index: 8468112 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2446. Min Range: -6.2446
Max Act: 5.7446. Min Act: -0.1700
Data Index: 2514479 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2446. Min Range: -6.2446
Max Act: 5.7134. Min Act: -0.1700
Data Index: 3396044 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19