Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2016 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2425. Min Range: -5.2425
Max Act: 5.2425. Min Act: -0.1700
Data Index: 469348 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2425. Min Range: -5.2425
Max Act: 5.2112. Min Act: -0.1700
Data Index: 3937034 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2425. Min Range: -5.2425
Max Act: 5.0550. Min Act: -0.1700
Data Index: 4119330 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2425. Min Range: -5.2425
Max Act: 4.9925. Min Act: -0.1700
Data Index: 1623952 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2425. Min Range: -5.2425
Max Act: 4.9612. Min Act: -0.1700
Data Index: 7686874 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2425. Min Range: -5.2425
Max Act: 4.9300. Min Act: -0.1700
Data Index: 8352342 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2425. Min Range: -5.2425
Max Act: 4.9300. Min Act: -0.1700
Data Index: 4116141 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2425. Min Range: -5.2425
Max Act: 4.9300. Min Act: -0.1700
Data Index: 4253777 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2425. Min Range: -5.2425
Max Act: 4.8675. Min Act: -0.1700
Data Index: 466826 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2425. Min Range: -5.2425
Max Act: 4.8675. Min Act: -0.1700
Data Index: 6000357 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2425. Min Range: -5.2425
Max Act: 4.8675. Min Act: -0.1700
Data Index: 5654959 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2425. Min Range: -5.2425
Max Act: 4.8362. Min Act: -0.1700
Data Index: 6690110 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2425. Min Range: -5.2425
Max Act: 4.8362. Min Act: -0.1700
Data Index: 1813184 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2425. Min Range: -5.2425
Max Act: 4.8362. Min Act: -0.1700
Data Index: 4609415 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2425. Min Range: -5.2425
Max Act: 4.8362. Min Act: -0.1700
Data Index: 8153064 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2425. Min Range: -5.2425
Max Act: 4.8050. Min Act: -0.1700
Data Index: 582369 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2425. Min Range: -5.2425
Max Act: 4.7425. Min Act: -0.1700
Data Index: 798164 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2425. Min Range: -5.2425
Max Act: 4.7112. Min Act: -0.1700
Data Index: 1688286 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2425. Min Range: -5.2425
Max Act: 4.7425. Min Act: -0.1700
Data Index: 1954492 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2425. Min Range: -5.2425
Max Act: 4.7425. Min Act: -0.1700
Data Index: 568609 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19