Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 85 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.8769. Min Range: -10.8769
Max Act: 10.8769. Min Act: -0.1700
Data Index: 2237356 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8769. Min Range: -10.8769
Max Act: 10.8144. Min Act: -0.1700
Data Index: 8115592 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8769. Min Range: -10.8769
Max Act: 10.7519. Min Act: -0.1700
Data Index: 7691962 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8769. Min Range: -10.8769
Max Act: 10.6269. Min Act: -0.1700
Data Index: 1710366 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8769. Min Range: -10.8769
Max Act: 10.5644. Min Act: -0.1700
Data Index: 80325 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8769. Min Range: -10.8769
Max Act: 10.5019. Min Act: -0.1700
Data Index: 7385563 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8769. Min Range: -10.8769
Max Act: 10.5019. Min Act: -0.1700
Data Index: 1914192 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8769. Min Range: -10.8769
Max Act: 10.5644. Min Act: -0.1700
Data Index: 6478245 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8769. Min Range: -10.8769
Max Act: 10.5019. Min Act: -0.1700
Data Index: 80324 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8769. Min Range: -10.8769
Max Act: 10.5644. Min Act: -0.1700
Data Index: 5974157 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8769. Min Range: -10.8769
Max Act: 10.3769. Min Act: -0.1700
Data Index: 5830517 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8769. Min Range: -10.8769
Max Act: 10.3769. Min Act: -0.1700
Data Index: 2199083 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8769. Min Range: -10.8769
Max Act: 10.3769. Min Act: -0.1700
Data Index: 1494935 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8769. Min Range: -10.8769
Max Act: 10.3769. Min Act: -0.1700
Data Index: 1304092 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8769. Min Range: -10.8769
Max Act: 10.3144. Min Act: -0.1700
Data Index: 1275507 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8769. Min Range: -10.8769
Max Act: 10.2519. Min Act: -0.1700
Data Index: 2409948 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8769. Min Range: -10.8769
Max Act: 10.2519. Min Act: -0.1700
Data Index: 2048216 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8769. Min Range: -10.8769
Max Act: 10.2519. Min Act: -0.1700
Data Index: 5504205 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8769. Min Range: -10.8769
Max Act: 10.2519. Min Act: -0.1700
Data Index: 5204283 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8769. Min Range: -10.8769
Max Act: 10.2519. Min Act: -0.1700
Data Index: 1977120 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19