Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3224 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4762. Min Range: -4.4762
Max Act: 4.4762. Min Act: -0.1700
Data Index: 7476360 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4762. Min Range: -4.4762
Max Act: 4.4762. Min Act: -0.1700
Data Index: 8564666 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4762. Min Range: -4.4762
Max Act: 4.3824. Min Act: -0.1700
Data Index: 420008 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4762. Min Range: -4.4762
Max Act: 4.3824. Min Act: -0.1700
Data Index: 1575051 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4762. Min Range: -4.4762
Max Act: 4.3512. Min Act: -0.1700
Data Index: 2457866 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4762. Min Range: -4.4762
Max Act: 4.3199. Min Act: -0.1700
Data Index: 6309373 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4762. Min Range: -4.4762
Max Act: 4.3199. Min Act: -0.1700
Data Index: 5270255 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4762. Min Range: -4.4762
Max Act: 4.2887. Min Act: -0.1700
Data Index: 2191180 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4762. Min Range: -4.4762
Max Act: 4.2887. Min Act: -0.1700
Data Index: 5877346 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4762. Min Range: -4.4762
Max Act: 4.2262. Min Act: -0.1700
Data Index: 2186304 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4762. Min Range: -4.4762
Max Act: 4.1012. Min Act: -0.1700
Data Index: 8458205 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4762. Min Range: -4.4762
Max Act: 4.0074. Min Act: -0.1700
Data Index: 5749267 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4762. Min Range: -4.4762
Max Act: 4.0074. Min Act: -0.1700
Data Index: 4236097 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4762. Min Range: -4.4762
Max Act: 4.0074. Min Act: -0.1700
Data Index: 695451 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4762. Min Range: -4.4762
Max Act: 3.9136. Min Act: -0.1700
Data Index: 4853616 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4762. Min Range: -4.4762
Max Act: 3.9136. Min Act: -0.1700
Data Index: 1184921 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4762. Min Range: -4.4762
Max Act: 3.8823. Min Act: -0.1700
Data Index: 4758507 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4762. Min Range: -4.4762
Max Act: 3.9136. Min Act: -0.1700
Data Index: 478049 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4762. Min Range: -4.4762
Max Act: 3.8511. Min Act: -0.1700
Data Index: 2845584 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4762. Min Range: -4.4762
Max Act: 3.8511. Min Act: -0.1700
Data Index: 3126297 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19