Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6376 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2466. Min Range: -2.2466
Max Act: 2.2466. Min Act: -0.1700
Data Index: 295118 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2466. Min Range: -2.2466
Max Act: 2.1470. Min Act: -0.1700
Data Index: 7429824 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2466. Min Range: -2.2466
Max Act: 2.1470. Min Act: -0.1700
Data Index: 4621507 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2466. Min Range: -2.2466
Max Act: 2.1470. Min Act: -0.1700
Data Index: 749154 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2466. Min Range: -2.2466
Max Act: 2.1304. Min Act: -0.1700
Data Index: 3346414 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2466. Min Range: -2.2466
Max Act: 2.1470. Min Act: -0.1700
Data Index: 6978004 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2466. Min Range: -2.2466
Max Act: 2.1136. Min Act: -0.1700
Data Index: 8441339 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2466. Min Range: -2.2466
Max Act: 2.0969. Min Act: -0.1700
Data Index: 2352186 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2466. Min Range: -2.2466
Max Act: 2.1136. Min Act: -0.1700
Data Index: 2293577 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2466. Min Range: -2.2466
Max Act: 2.1136. Min Act: -0.1700
Data Index: 3692249 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2466. Min Range: -2.2466
Max Act: 2.1304. Min Act: -0.1700
Data Index: 3052576 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2466. Min Range: -2.2466
Max Act: 2.0969. Min Act: -0.1700
Data Index: 367668 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2466. Min Range: -2.2466
Max Act: 2.1136. Min Act: -0.1700
Data Index: 908429 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2466. Min Range: -2.2466
Max Act: 2.0969. Min Act: -0.1700
Data Index: 6261553 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2466. Min Range: -2.2466
Max Act: 2.1136. Min Act: -0.1700
Data Index: 4922595 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2466. Min Range: -2.2466
Max Act: 2.0969. Min Act: -0.1700
Data Index: 812533 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2466. Min Range: -2.2466
Max Act: 2.0801. Min Act: -0.1700
Data Index: 3559596 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2466. Min Range: -2.2466
Max Act: 2.0801. Min Act: -0.1700
Data Index: 3362663 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2466. Min Range: -2.2466
Max Act: 2.0969. Min Act: -0.1700
Data Index: 5373241 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2466. Min Range: -2.2466
Max Act: 2.0801. Min Act: -0.1700
Data Index: 1127762 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19