Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4407 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8769. Min Range: -4.8769
Max Act: 4.8769. Min Act: -0.1700
Data Index: 2758855 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8769. Min Range: -4.8769
Max Act: 4.8769. Min Act: -0.1700
Data Index: 5143936 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8769. Min Range: -4.8769
Max Act: 4.8457. Min Act: -0.1700
Data Index: 8110423 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8769. Min Range: -4.8769
Max Act: 4.8144. Min Act: -0.1700
Data Index: 614842 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8769. Min Range: -4.8769
Max Act: 4.7832. Min Act: -0.1699
Data Index: 1968022 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8769. Min Range: -4.8769
Max Act: 4.7832. Min Act: -0.1700
Data Index: 3599726 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8769. Min Range: -4.8769
Max Act: 4.7832. Min Act: -0.1700
Data Index: 837004 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8769. Min Range: -4.8769
Max Act: 4.7832. Min Act: -0.1700
Data Index: 2758854 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8769. Min Range: -4.8769
Max Act: 4.7519. Min Act: -0.1700
Data Index: 4598952 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8769. Min Range: -4.8769
Max Act: 4.7519. Min Act: -0.1700
Data Index: 4598940 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8769. Min Range: -4.8769
Max Act: 4.7519. Min Act: -0.1700
Data Index: 3026298 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8769. Min Range: -4.8769
Max Act: 4.7519. Min Act: -0.1700
Data Index: 8082850 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8769. Min Range: -4.8769
Max Act: 4.7519. Min Act: -0.1700
Data Index: 7016999 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8769. Min Range: -4.8769
Max Act: 4.7519. Min Act: -0.1700
Data Index: 6139135 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8769. Min Range: -4.8769
Max Act: 4.7207. Min Act: -0.1700
Data Index: 1968050 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8769. Min Range: -4.8769
Max Act: 4.7207. Min Act: -0.1700
Data Index: 5679774 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8769. Min Range: -4.8769
Max Act: 4.7519. Min Act: -0.1700
Data Index: 1248060 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8769. Min Range: -4.8769
Max Act: 4.7207. Min Act: -0.1700
Data Index: 3626694 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8769. Min Range: -4.8769
Max Act: 4.6894. Min Act: -0.1700
Data Index: 2601114 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8769. Min Range: -4.8769
Max Act: 4.6894. Min Act: -0.1700
Data Index: 2658328 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19