Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3133 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6561. Min Range: -7.6561
Max Act: 7.6561. Min Act: -0.1700
Data Index: 5504585 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6561. Min Range: -7.6561
Max Act: 7.5936. Min Act: -0.1700
Data Index: 2990039 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6561. Min Range: -7.6561
Max Act: 7.4686. Min Act: -0.1700
Data Index: 820072 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6561. Min Range: -7.6561
Max Act: 7.4061. Min Act: -0.1700
Data Index: 2756351 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6561. Min Range: -7.6561
Max Act: 7.2811. Min Act: -0.1700
Data Index: 4033527 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6561. Min Range: -7.6561
Max Act: 7.2811. Min Act: -0.1700
Data Index: 8050194 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6561. Min Range: -7.6561
Max Act: 7.2811. Min Act: -0.1700
Data Index: 1344330 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6561. Min Range: -7.6561
Max Act: 7.2811. Min Act: -0.1700
Data Index: 8523639 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6561. Min Range: -7.6561
Max Act: 7.2186. Min Act: -0.1700
Data Index: 1294338 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6561. Min Range: -7.6561
Max Act: 7.1873. Min Act: -0.1700
Data Index: 6747506 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6561. Min Range: -7.6561
Max Act: 7.2186. Min Act: -0.1700
Data Index: 5595632 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6561. Min Range: -7.6561
Max Act: 7.1873. Min Act: -0.1700
Data Index: 2602165 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6561. Min Range: -7.6561
Max Act: 7.1561. Min Act: -0.1700
Data Index: 3463596 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6561. Min Range: -7.6561
Max Act: 7.1248. Min Act: -0.1700
Data Index: 7965682 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6561. Min Range: -7.6561
Max Act: 7.1248. Min Act: -0.1700
Data Index: 7854028 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6561. Min Range: -7.6561
Max Act: 7.0936. Min Act: -0.1700
Data Index: 5686710 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6561. Min Range: -7.6561
Max Act: 7.0623. Min Act: -0.1700
Data Index: 7341666 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6561. Min Range: -7.6561
Max Act: 7.0623. Min Act: -0.1700
Data Index: 5531154 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6561. Min Range: -7.6561
Max Act: 7.0311. Min Act: -0.1700
Data Index: 2996981 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6561. Min Range: -7.6561
Max Act: 7.0311. Min Act: -0.1700
Data Index: 117023 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19