Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 145 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2249. Min Range: -5.2249
Max Act: 5.1937. Min Act: -0.1700
Data Index: 2190411 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2249. Min Range: -5.2249
Max Act: 5.2249. Min Act: -0.1700
Data Index: 3364151 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2249. Min Range: -5.2249
Max Act: 5.1937. Min Act: -0.1700
Data Index: 4807662 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2249. Min Range: -5.2249
Max Act: 5.1937. Min Act: -0.1700
Data Index: 7418304 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2249. Min Range: -5.2249
Max Act: 5.1624. Min Act: -0.1700
Data Index: 2704281 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2249. Min Range: -5.2249
Max Act: 5.1624. Min Act: -0.1700
Data Index: 4752009 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2249. Min Range: -5.2249
Max Act: 5.1624. Min Act: -0.1700
Data Index: 4245225 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2249. Min Range: -5.2249
Max Act: 5.1312. Min Act: -0.1700
Data Index: 7488826 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2249. Min Range: -5.2249
Max Act: 5.1312. Min Act: -0.1700
Data Index: 7717792 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2249. Min Range: -5.2249
Max Act: 5.0999. Min Act: -0.1700
Data Index: 5247571 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2249. Min Range: -5.2249
Max Act: 5.0687. Min Act: -0.1700
Data Index: 806566 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2249. Min Range: -5.2249
Max Act: 5.0999. Min Act: -0.1700
Data Index: 2130823 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2249. Min Range: -5.2249
Max Act: 5.0999. Min Act: -0.1700
Data Index: 3125092 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2249. Min Range: -5.2249
Max Act: 5.0999. Min Act: -0.1700
Data Index: 455871 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2249. Min Range: -5.2249
Max Act: 5.0999. Min Act: -0.1700
Data Index: 1404445 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2249. Min Range: -5.2249
Max Act: 5.0687. Min Act: -0.1700
Data Index: 7356206 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2249. Min Range: -5.2249
Max Act: 5.0687. Min Act: -0.1700
Data Index: 1322676 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2249. Min Range: -5.2249
Max Act: 5.0687. Min Act: -0.1700
Data Index: 4457280 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2249. Min Range: -5.2249
Max Act: 5.0687. Min Act: -0.1700
Data Index: 479171 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2249. Min Range: -5.2249
Max Act: 5.0687. Min Act: -0.1700
Data Index: 2591018 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19