Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 590 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4968. Min Range: -8.4968
Max Act: 8.4968. Min Act: -0.1700
Data Index: 7542644 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4968. Min Range: -8.4968
Max Act: 8.3093. Min Act: -0.1700
Data Index: 1457319 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4968. Min Range: -8.4968
Max Act: 8.2468. Min Act: -0.1700
Data Index: 70865 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4968. Min Range: -8.4968
Max Act: 8.1218. Min Act: -0.1700
Data Index: 1853154 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4968. Min Range: -8.4968
Max Act: 7.9968. Min Act: -0.1700
Data Index: 1284670 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4968. Min Range: -8.4968
Max Act: 7.9343. Min Act: -0.1700
Data Index: 4857104 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4968. Min Range: -8.4968
Max Act: 7.9343. Min Act: -0.1700
Data Index: 4670133 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4968. Min Range: -8.4968
Max Act: 7.9343. Min Act: -0.1700
Data Index: 3974230 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4968. Min Range: -8.4968
Max Act: 7.9031. Min Act: -0.1700
Data Index: 7519613 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4968. Min Range: -8.4968
Max Act: 7.9031. Min Act: -0.1700
Data Index: 4173534 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4968. Min Range: -8.4968
Max Act: 7.9031. Min Act: -0.1700
Data Index: 413232 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4968. Min Range: -8.4968
Max Act: 7.9031. Min Act: -0.1700
Data Index: 1957220 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4968. Min Range: -8.4968
Max Act: 7.8718. Min Act: -0.1700
Data Index: 4116497 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4968. Min Range: -8.4968
Max Act: 7.8718. Min Act: -0.1700
Data Index: 5758351 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4968. Min Range: -8.4968
Max Act: 7.8406. Min Act: -0.1700
Data Index: 1272857 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4968. Min Range: -8.4968
Max Act: 7.8406. Min Act: -0.1700
Data Index: 7194439 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4968. Min Range: -8.4968
Max Act: 7.8406. Min Act: -0.1700
Data Index: 500004 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4968. Min Range: -8.4968
Max Act: 7.8406. Min Act: -0.1700
Data Index: 3839714 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4968. Min Range: -8.4968
Max Act: 7.8718. Min Act: -0.1700
Data Index: 1326752 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4968. Min Range: -8.4968
Max Act: 7.8406. Min Act: -0.1700
Data Index: 8600599 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19