Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1696 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1425. Min Range: -9.1425
Max Act: 9.1425. Min Act: -0.1700
Data Index: 6701862 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1425. Min Range: -9.1425
Max Act: 8.9550. Min Act: -0.1700
Data Index: 420019 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1425. Min Range: -9.1425
Max Act: 8.8300. Min Act: -0.1700
Data Index: 2530809 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1425. Min Range: -9.1425
Max Act: 8.8300. Min Act: -0.1700
Data Index: 63036 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1425. Min Range: -9.1425
Max Act: 8.8300. Min Act: -0.1700
Data Index: 849832 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1425. Min Range: -9.1425
Max Act: 8.6425. Min Act: -0.1700
Data Index: 8424713 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1425. Min Range: -9.1425
Max Act: 8.6425. Min Act: -0.1700
Data Index: 1116398 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1425. Min Range: -9.1425
Max Act: 8.5800. Min Act: -0.1700
Data Index: 2973811 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1425. Min Range: -9.1425
Max Act: 8.5175. Min Act: -0.1700
Data Index: 1823723 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1425. Min Range: -9.1425
Max Act: 8.4550. Min Act: -0.1700
Data Index: 486300 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1425. Min Range: -9.1425
Max Act: 8.3925. Min Act: -0.1700
Data Index: 5432859 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1425. Min Range: -9.1425
Max Act: 8.3300. Min Act: -0.1700
Data Index: 7302534 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1425. Min Range: -9.1425
Max Act: 8.3300. Min Act: -0.1700
Data Index: 4835210 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1425. Min Range: -9.1425
Max Act: 8.3300. Min Act: -0.1700
Data Index: 2062080 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1425. Min Range: -9.1425
Max Act: 8.2675. Min Act: -0.1700
Data Index: 5886612 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1425. Min Range: -9.1425
Max Act: 8.2675. Min Act: -0.1700
Data Index: 5464679 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1425. Min Range: -9.1425
Max Act: 8.2675. Min Act: -0.1700
Data Index: 1859960 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1425. Min Range: -9.1425
Max Act: 8.2050. Min Act: -0.1700
Data Index: 8080914 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1425. Min Range: -9.1425
Max Act: 8.2050. Min Act: -0.1700
Data Index: 4170092 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1425. Min Range: -9.1425
Max Act: 8.2050. Min Act: -0.1700
Data Index: 5611323 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19