Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1394 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6397. Min Range: -5.6397
Max Act: 5.6397. Min Act: -0.1700
Data Index: 368826 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6397. Min Range: -5.6397
Max Act: 5.4522. Min Act: -0.1700
Data Index: 3010677 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6397. Min Range: -5.6397
Max Act: 5.3897. Min Act: -0.1700
Data Index: 5310485 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6397. Min Range: -5.6397
Max Act: 5.3585. Min Act: -0.1700
Data Index: 4534878 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6397. Min Range: -5.6397
Max Act: 5.2960. Min Act: -0.1700
Data Index: 3687812 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6397. Min Range: -5.6397
Max Act: 5.2647. Min Act: -0.1700
Data Index: 1863572 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6397. Min Range: -5.6397
Max Act: 5.2335. Min Act: -0.1700
Data Index: 2493773 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6397. Min Range: -5.6397
Max Act: 5.2022. Min Act: -0.1700
Data Index: 6448682 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6397. Min Range: -5.6397
Max Act: 5.2335. Min Act: -0.1700
Data Index: 629206 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6397. Min Range: -5.6397
Max Act: 5.2335. Min Act: -0.1700
Data Index: 6579409 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6397. Min Range: -5.6397
Max Act: 5.1397. Min Act: -0.1700
Data Index: 1025242 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6397. Min Range: -5.6397
Max Act: 5.1710. Min Act: -0.1700
Data Index: 2844983 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6397. Min Range: -5.6397
Max Act: 5.1710. Min Act: -0.1700
Data Index: 8627066 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6397. Min Range: -5.6397
Max Act: 5.1397. Min Act: -0.1700
Data Index: 5725328 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6397. Min Range: -5.6397
Max Act: 5.1085. Min Act: -0.1700
Data Index: 6350207 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6397. Min Range: -5.6397
Max Act: 5.1085. Min Act: -0.1700
Data Index: 7143653 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6397. Min Range: -5.6397
Max Act: 5.0772. Min Act: -0.1700
Data Index: 7387668 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6397. Min Range: -5.6397
Max Act: 5.0772. Min Act: -0.1700
Data Index: 2599208 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6397. Min Range: -5.6397
Max Act: 5.0772. Min Act: -0.1700
Data Index: 2769896 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6397. Min Range: -5.6397
Max Act: 5.0772. Min Act: -0.1700
Data Index: 2600106 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19