Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 995 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2387. Min Range: -6.2387
Max Act: 6.2387. Min Act: -0.1700
Data Index: 4302008 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2387. Min Range: -6.2387
Max Act: 6.2074. Min Act: -0.1700
Data Index: 1610127 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2387. Min Range: -6.2387
Max Act: 6.2074. Min Act: -0.1700
Data Index: 290874 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2387. Min Range: -6.2387
Max Act: 5.9887. Min Act: -0.1700
Data Index: 1610110 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2387. Min Range: -6.2387
Max Act: 5.9574. Min Act: -0.1700
Data Index: 1158233 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2387. Min Range: -6.2387
Max Act: 5.9262. Min Act: -0.1700
Data Index: 7745323 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2387. Min Range: -6.2387
Max Act: 5.9574. Min Act: -0.1700
Data Index: 3136878 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2387. Min Range: -6.2387
Max Act: 5.9262. Min Act: -0.1700
Data Index: 1610116 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2387. Min Range: -6.2387
Max Act: 5.9262. Min Act: -0.1700
Data Index: 3355834 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2387. Min Range: -6.2387
Max Act: 5.8949. Min Act: -0.1700
Data Index: 1610108 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2387. Min Range: -6.2387
Max Act: 5.8637. Min Act: -0.1700
Data Index: 6379225 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2387. Min Range: -6.2387
Max Act: 5.8012. Min Act: -0.1700
Data Index: 6617660 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2387. Min Range: -6.2387
Max Act: 5.7699. Min Act: -0.1700
Data Index: 6531173 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2387. Min Range: -6.2387
Max Act: 5.8012. Min Act: -0.1700
Data Index: 4598789 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2387. Min Range: -6.2387
Max Act: 5.7699. Min Act: -0.1700
Data Index: 6548182 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2387. Min Range: -6.2387
Max Act: 5.7387. Min Act: -0.1700
Data Index: 6735114 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2387. Min Range: -6.2387
Max Act: 5.7387. Min Act: -0.1700
Data Index: 263696 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2387. Min Range: -6.2387
Max Act: 5.7387. Min Act: -0.1700
Data Index: 5010599 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2387. Min Range: -6.2387
Max Act: 5.7699. Min Act: -0.1700
Data Index: 5218755 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2387. Min Range: -6.2387
Max Act: 5.7387. Min Act: -0.1700
Data Index: 4368257 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19