Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 614 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2325. Min Range: -6.2325
Max Act: 6.2325. Min Act: -0.1700
Data Index: 7673108 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2325. Min Range: -6.2325
Max Act: 6.0763. Min Act: -0.1700
Data Index: 1837154 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2325. Min Range: -6.2325
Max Act: 6.0450. Min Act: -0.1700
Data Index: 914690 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2325. Min Range: -6.2325
Max Act: 5.8575. Min Act: -0.1700
Data Index: 4510691 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2325. Min Range: -6.2325
Max Act: 5.8263. Min Act: -0.1700
Data Index: 3922487 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2325. Min Range: -6.2325
Max Act: 5.8263. Min Act: -0.1700
Data Index: 5494962 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2325. Min Range: -6.2325
Max Act: 5.7950. Min Act: -0.1700
Data Index: 903242 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2325. Min Range: -6.2325
Max Act: 5.7638. Min Act: -0.1700
Data Index: 8038407 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2325. Min Range: -6.2325
Max Act: 5.7950. Min Act: -0.1700
Data Index: 2975000 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2325. Min Range: -6.2325
Max Act: 5.7638. Min Act: -0.1700
Data Index: 1322404 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2325. Min Range: -6.2325
Max Act: 5.7013. Min Act: -0.1700
Data Index: 8257661 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2325. Min Range: -6.2325
Max Act: 5.6700. Min Act: -0.1700
Data Index: 8434644 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2325. Min Range: -6.2325
Max Act: 5.6700. Min Act: -0.1700
Data Index: 6910392 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2325. Min Range: -6.2325
Max Act: 5.6700. Min Act: -0.1700
Data Index: 254769 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2325. Min Range: -6.2325
Max Act: 5.6388. Min Act: -0.1700
Data Index: 6785972 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2325. Min Range: -6.2325
Max Act: 5.6388. Min Act: -0.1700
Data Index: 7987015 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2325. Min Range: -6.2325
Max Act: 5.6388. Min Act: -0.1700
Data Index: 1973151 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2325. Min Range: -6.2325
Max Act: 5.6700. Min Act: -0.1700
Data Index: 988711 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2325. Min Range: -6.2325
Max Act: 5.6388. Min Act: -0.1700
Data Index: 8529463 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2325. Min Range: -6.2325
Max Act: 5.6075. Min Act: -0.1700
Data Index: 3480805 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19