Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 515 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.7555. Min Act: -0.1700
Data Index: 4347848 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.6305. Min Act: -0.1700
Data Index: 8077138 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.6305. Min Act: -0.1700
Data Index: 3099105 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.5680. Min Act: -0.1700
Data Index: 7826360 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.5055. Min Act: -0.1700
Data Index: 7907903 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.4743. Min Act: -0.1700
Data Index: 4956786 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.4743. Min Act: -0.1700
Data Index: 1949427 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.4118. Min Act: -0.1700
Data Index: 1378007 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.3805. Min Act: -0.1700
Data Index: 8827203 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.4118. Min Act: -0.1700
Data Index: 7787364 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.3493. Min Act: -0.1700
Data Index: 7617122 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.2868. Min Act: -0.1700
Data Index: 1582544 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.2868. Min Act: -0.1700
Data Index: 2955046 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.3180. Min Act: -0.1700
Data Index: 5793742 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.2555. Min Act: -0.1700
Data Index: 8817714 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.2555. Min Act: -0.1700
Data Index: 4688557 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.2243. Min Act: -0.1700
Data Index: 634341 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.2243. Min Act: -0.1700
Data Index: 142249 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.2243. Min Act: -0.1700
Data Index: 6166344 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.1930. Min Act: -0.1700
Data Index: 4901144 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19