Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2587 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4889. Min Range: -4.4889
Max Act: 4.4889. Min Act: -0.1700
Data Index: 8545480 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4889. Min Range: -4.4889
Max Act: 4.3639. Min Act: -0.1700
Data Index: 6602200 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4889. Min Range: -4.4889
Max Act: 4.3327. Min Act: -0.1700
Data Index: 6155055 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4889. Min Range: -4.4889
Max Act: 4.2702. Min Act: -0.1700
Data Index: 1326518 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4889. Min Range: -4.4889
Max Act: 4.3014. Min Act: -0.1700
Data Index: 6886145 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4889. Min Range: -4.4889
Max Act: 4.2702. Min Act: -0.1700
Data Index: 1266441 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4889. Min Range: -4.4889
Max Act: 4.2702. Min Act: -0.1700
Data Index: 3022757 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4889. Min Range: -4.4889
Max Act: 4.2389. Min Act: -0.1700
Data Index: 3934769 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4889. Min Range: -4.4889
Max Act: 4.2702. Min Act: -0.1700
Data Index: 6130879 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4889. Min Range: -4.4889
Max Act: 4.2077. Min Act: -0.1700
Data Index: 5384214 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4889. Min Range: -4.4889
Max Act: 4.2389. Min Act: -0.1700
Data Index: 2094267 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4889. Min Range: -4.4889
Max Act: 4.2389. Min Act: -0.1700
Data Index: 3943192 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4889. Min Range: -4.4889
Max Act: 4.2077. Min Act: -0.1700
Data Index: 281738 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4889. Min Range: -4.4889
Max Act: 4.2077. Min Act: -0.1700
Data Index: 6914865 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4889. Min Range: -4.4889
Max Act: 4.2077. Min Act: -0.1700
Data Index: 2262974 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4889. Min Range: -4.4889
Max Act: 4.2077. Min Act: -0.1700
Data Index: 2205455 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4889. Min Range: -4.4889
Max Act: 4.1139. Min Act: -0.1700
Data Index: 152457 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4889. Min Range: -4.4889
Max Act: 4.1764. Min Act: -0.1700
Data Index: 3389541 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4889. Min Range: -4.4889
Max Act: 4.1139. Min Act: -0.1700
Data Index: 861692 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4889. Min Range: -4.4889
Max Act: 4.1452. Min Act: -0.1700
Data Index: 1458338 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19