Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3589 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9034. Min Range: -3.9034
Max Act: 3.9034. Min Act: -0.1700
Data Index: 7356082 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9034. Min Range: -3.9034
Max Act: 3.7158. Min Act: -0.1700
Data Index: 901581 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9034. Min Range: -3.9034
Max Act: 3.7158. Min Act: -0.1700
Data Index: 6610142 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9034. Min Range: -3.9034
Max Act: 3.6845. Min Act: -0.1700
Data Index: 8806730 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9034. Min Range: -3.9034
Max Act: 3.6063. Min Act: -0.1700
Data Index: 3143377 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9034. Min Range: -3.9034
Max Act: 3.5906. Min Act: -0.1700
Data Index: 2784692 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9034. Min Range: -3.9034
Max Act: 3.6532. Min Act: -0.1700
Data Index: 5595024 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9034. Min Range: -3.9034
Max Act: 3.6219. Min Act: -0.1700
Data Index: 4763271 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9034. Min Range: -3.9034
Max Act: 3.5749. Min Act: -0.1700
Data Index: 4745078 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9034. Min Range: -3.9034
Max Act: 3.5906. Min Act: -0.1700
Data Index: 2488419 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9034. Min Range: -3.9034
Max Act: 3.5749. Min Act: -0.1700
Data Index: 5143333 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9034. Min Range: -3.9034
Max Act: 3.5749. Min Act: -0.1700
Data Index: 263137 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9034. Min Range: -3.9034
Max Act: 3.4810. Min Act: -0.1700
Data Index: 7161901 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9034. Min Range: -3.9034
Max Act: 3.5123. Min Act: -0.1700
Data Index: 1102016 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9034. Min Range: -3.9034
Max Act: 3.5436. Min Act: -0.1700
Data Index: 6567573 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9034. Min Range: -3.9034
Max Act: 3.5123. Min Act: -0.1700
Data Index: 957890 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9034. Min Range: -3.9034
Max Act: 3.5436. Min Act: -0.1696
Data Index: 3487728 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9034. Min Range: -3.9034
Max Act: 3.5123. Min Act: -0.1700
Data Index: 7713004 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9034. Min Range: -3.9034
Max Act: 3.4810. Min Act: -0.1698
Data Index: 916361 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9034. Min Range: -3.9034
Max Act: 3.4497. Min Act: -0.1700
Data Index: 8137212 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19