Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1739 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2902. Min Range: -8.2902
Max Act: 8.2902. Min Act: -0.1700
Data Index: 1697367 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2902. Min Range: -8.2902
Max Act: 8.2277. Min Act: -0.1700
Data Index: 869154 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2902. Min Range: -8.2902
Max Act: 8.1652. Min Act: -0.1700
Data Index: 8368467 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2902. Min Range: -8.2902
Max Act: 8.1652. Min Act: -0.1700
Data Index: 1550889 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2902. Min Range: -8.2902
Max Act: 7.7277. Min Act: -0.1700
Data Index: 6425938 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2902. Min Range: -8.2902
Max Act: 7.6652. Min Act: -0.1700
Data Index: 750998 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2902. Min Range: -8.2902
Max Act: 7.6652. Min Act: -0.1700
Data Index: 2740280 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2902. Min Range: -8.2902
Max Act: 7.6339. Min Act: -0.1700
Data Index: 8681434 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2902. Min Range: -8.2902
Max Act: 7.5714. Min Act: -0.1700
Data Index: 358330 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2902. Min Range: -8.2902
Max Act: 7.5402. Min Act: -0.1700
Data Index: 561928 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2902. Min Range: -8.2902
Max Act: 7.5402. Min Act: -0.1700
Data Index: 22981 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2902. Min Range: -8.2902
Max Act: 7.5089. Min Act: -0.1700
Data Index: 5971090 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2902. Min Range: -8.2902
Max Act: 7.5089. Min Act: -0.1700
Data Index: 5180914 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2902. Min Range: -8.2902
Max Act: 7.5089. Min Act: -0.1700
Data Index: 6425937 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2902. Min Range: -8.2902
Max Act: 7.4777. Min Act: -0.1700
Data Index: 7517124 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2902. Min Range: -8.2902
Max Act: 7.4464. Min Act: -0.1700
Data Index: 2638429 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2902. Min Range: -8.2902
Max Act: 7.3839. Min Act: -0.1700
Data Index: 8366647 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2902. Min Range: -8.2902
Max Act: 7.3839. Min Act: -0.1700
Data Index: 8517518 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2902. Min Range: -8.2902
Max Act: 7.3214. Min Act: -0.1700
Data Index: 4873348 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2902. Min Range: -8.2902
Max Act: 7.3214. Min Act: -0.1700
Data Index: 5964534 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19