Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2004 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.9622. Min Act: -0.1700
Data Index: 5557974 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.7435. Min Act: -0.1700
Data Index: 6627703 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.7122. Min Act: -0.1700
Data Index: 3805758 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.6497. Min Act: -0.1700
Data Index: 6169303 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.5560. Min Act: -0.1700
Data Index: 4799289 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.5560. Min Act: -0.1700
Data Index: 2585921 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.5247. Min Act: -0.1700
Data Index: 1038236 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.4935. Min Act: -0.1700
Data Index: 2246174 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.4622. Min Act: -0.1700
Data Index: 8777547 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.4310. Min Act: -0.1700
Data Index: 558519 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.4310. Min Act: -0.1700
Data Index: 7400124 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.3997. Min Act: -0.1700
Data Index: 7790155 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.3372. Min Act: -0.1700
Data Index: 1524316 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.3060. Min Act: -0.1700
Data Index: 3837683 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.3060. Min Act: -0.1700
Data Index: 6048166 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.3372. Min Act: -0.1700
Data Index: 8303472 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.3060. Min Act: -0.1700
Data Index: 7467677 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.3060. Min Act: -0.1700
Data Index: 4234655 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.3060. Min Act: -0.1700
Data Index: 1442076 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9622. Min Range: -5.9622
Max Act: 5.3060. Min Act: -0.1700
Data Index: 686959 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19