Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3904 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6976. Min Range: -6.6976
Max Act: 6.6976. Min Act: -0.1700
Data Index: 1081205 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6976. Min Range: -6.6976
Max Act: 6.6663. Min Act: -0.1700
Data Index: 1081207 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6976. Min Range: -6.6976
Max Act: 6.6038. Min Act: -0.1700
Data Index: 1081202 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6976. Min Range: -6.6976
Max Act: 6.4788. Min Act: -0.1700
Data Index: 496243 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6976. Min Range: -6.6976
Max Act: 6.2913. Min Act: -0.1700
Data Index: 8738177 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6976. Min Range: -6.6976
Max Act: 6.1976. Min Act: -0.1700
Data Index: 2273130 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6976. Min Range: -6.6976
Max Act: 6.1976. Min Act: -0.1700
Data Index: 2001476 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6976. Min Range: -6.6976
Max Act: 6.1976. Min Act: -0.1700
Data Index: 8349019 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6976. Min Range: -6.6976
Max Act: 6.1663. Min Act: -0.1700
Data Index: 1081203 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6976. Min Range: -6.6976
Max Act: 6.1351. Min Act: -0.1700
Data Index: 4312430 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6976. Min Range: -6.6976
Max Act: 6.1351. Min Act: -0.1700
Data Index: 1313442 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6976. Min Range: -6.6976
Max Act: 6.1351. Min Act: -0.1700
Data Index: 8097965 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6976. Min Range: -6.6976
Max Act: 6.1038. Min Act: -0.1700
Data Index: 7222788 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6976. Min Range: -6.6976
Max Act: 6.0726. Min Act: -0.1700
Data Index: 4824073 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6976. Min Range: -6.6976
Max Act: 6.0413. Min Act: -0.1700
Data Index: 6043991 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6976. Min Range: -6.6976
Max Act: 6.0413. Min Act: -0.1700
Data Index: 8731362 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6976. Min Range: -6.6976
Max Act: 6.0101. Min Act: -0.1700
Data Index: 6418017 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6976. Min Range: -6.6976
Max Act: 6.0413. Min Act: -0.1700
Data Index: 496253 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6976. Min Range: -6.6976
Max Act: 6.0413. Min Act: -0.1700
Data Index: 4850131 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6976. Min Range: -6.6976
Max Act: 6.0101. Min Act: -0.1700
Data Index: 5214952 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19