Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2667 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.7138. Min Act: -0.1700
Data Index: 8599513 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.5263. Min Act: -0.1700
Data Index: 790238 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.4326. Min Act: -0.1700
Data Index: 6268909 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.3388. Min Act: -0.1700
Data Index: 3630224 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.2763. Min Act: -0.1700
Data Index: 8599506 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.3076. Min Act: -0.1700
Data Index: 1669987 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.2763. Min Act: -0.1700
Data Index: 2010219 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.3076. Min Act: -0.1700
Data Index: 6268907 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.2138. Min Act: -0.1700
Data Index: 4753086 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.2138. Min Act: -0.1700
Data Index: 137972 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.2138. Min Act: -0.1700
Data Index: 1473137 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.1826. Min Act: -0.1700
Data Index: 6268906 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.1513. Min Act: -0.1700
Data Index: 3943704 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.1826. Min Act: -0.1700
Data Index: 971378 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.1513. Min Act: -0.1700
Data Index: 6268898 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.1201. Min Act: -0.1700
Data Index: 6892281 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.1513. Min Act: -0.1700
Data Index: 3868052 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.1201. Min Act: -0.1700
Data Index: 2515905 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.0888. Min Act: -0.1700
Data Index: 6268908 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.0576. Min Act: -0.1700
Data Index: 4283301 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19