Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4762 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.7940. Min Act: -0.1700
Data Index: 7140666 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.6219. Min Act: -0.1700
Data Index: 5775604 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.5280. Min Act: -0.1700
Data Index: 123897 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.5280. Min Act: -0.1700
Data Index: 3861464 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.5280. Min Act: -0.1700
Data Index: 7895709 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.5123. Min Act: -0.1700
Data Index: 444896 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.5280. Min Act: -0.1700
Data Index: 3810686 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4967. Min Act: -0.1700
Data Index: 3522448 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4967. Min Act: -0.1700
Data Index: 4988048 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4810. Min Act: -0.1700
Data Index: 6278168 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4810. Min Act: -0.1700
Data Index: 2656960 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4497. Min Act: -0.1700
Data Index: 87097 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4497. Min Act: -0.1700
Data Index: 2757965 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4497. Min Act: -0.1700
Data Index: 7706892 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4340. Min Act: -0.1700
Data Index: 7858666 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4340. Min Act: -0.1700
Data Index: 5258202 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4183. Min Act: -0.1700
Data Index: 974722 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4183. Min Act: -0.1700
Data Index: 1475218 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4183. Min Act: -0.1700
Data Index: 8099616 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4027. Min Act: -0.1700
Data Index: 2594211 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19