Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2178 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7020. Min Range: -6.7020
Max Act: 6.7020. Min Act: -0.1700
Data Index: 7559508 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7020. Min Range: -6.7020
Max Act: 6.2333. Min Act: -0.1700
Data Index: 1091190 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7020. Min Range: -6.7020
Max Act: 6.0145. Min Act: -0.1700
Data Index: 1251041 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7020. Min Range: -6.7020
Max Act: 6.0458. Min Act: -0.1700
Data Index: 1353090 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7020. Min Range: -6.7020
Max Act: 6.0145. Min Act: -0.1700
Data Index: 71342 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7020. Min Range: -6.7020
Max Act: 5.9833. Min Act: -0.1700
Data Index: 7854220 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7020. Min Range: -6.7020
Max Act: 5.9520. Min Act: -0.1700
Data Index: 7602989 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7020. Min Range: -6.7020
Max Act: 5.9208. Min Act: -0.1700
Data Index: 6702387 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7020. Min Range: -6.7020
Max Act: 5.9520. Min Act: -0.1700
Data Index: 8195290 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7020. Min Range: -6.7020
Max Act: 5.8895. Min Act: -0.1700
Data Index: 6059871 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7020. Min Range: -6.7020
Max Act: 5.9208. Min Act: -0.1700
Data Index: 6059870 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7020. Min Range: -6.7020
Max Act: 5.8895. Min Act: -0.1700
Data Index: 1695177 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7020. Min Range: -6.7020
Max Act: 5.8895. Min Act: -0.1700
Data Index: 347677 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7020. Min Range: -6.7020
Max Act: 5.8895. Min Act: -0.1700
Data Index: 8666576 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7020. Min Range: -6.7020
Max Act: 5.8583. Min Act: -0.1700
Data Index: 4880253 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7020. Min Range: -6.7020
Max Act: 5.8583. Min Act: -0.1700
Data Index: 8823950 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7020. Min Range: -6.7020
Max Act: 5.8583. Min Act: -0.1700
Data Index: 7562888 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7020. Min Range: -6.7020
Max Act: 5.8583. Min Act: -0.1700
Data Index: 1547838 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7020. Min Range: -6.7020
Max Act: 5.8895. Min Act: -0.1700
Data Index: 3437042 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7020. Min Range: -6.7020
Max Act: 5.8270. Min Act: -0.1700
Data Index: 6919320 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19