Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4907 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.2851. Min Range: -1.2851
Max Act: 1.2498. Min Act: -0.1700
Data Index: 7148552 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2851. Min Range: -1.2851
Max Act: 1.2851. Min Act: -0.1700
Data Index: 3446231 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2851. Min Range: -1.2851
Max Act: 1.2498. Min Act: -0.1700
Data Index: 2958168 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2851. Min Range: -1.2851
Max Act: 1.2498. Min Act: -0.1700
Data Index: 2632389 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2851. Min Range: -1.2851
Max Act: 1.2322. Min Act: -0.1700
Data Index: 3646443 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2851. Min Range: -1.2851
Max Act: 1.2322. Min Act: -0.1700
Data Index: 6204759 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2851. Min Range: -1.2851
Max Act: 1.2322. Min Act: -0.1700
Data Index: 5789292 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2851. Min Range: -1.2851
Max Act: 1.2146. Min Act: -0.1700
Data Index: 341027 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2851. Min Range: -1.2851
Max Act: 1.2322. Min Act: -0.1700
Data Index: 7635325 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2851. Min Range: -1.2851
Max Act: 1.2146. Min Act: -0.1700
Data Index: 1561164 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2851. Min Range: -1.2851
Max Act: 1.2146. Min Act: -0.1700
Data Index: 6936670 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2851. Min Range: -1.2851
Max Act: 1.2146. Min Act: -0.1700
Data Index: 365418 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2851. Min Range: -1.2851
Max Act: 1.2146. Min Act: -0.1700
Data Index: 5208251 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2851. Min Range: -1.2851
Max Act: 1.2146. Min Act: -0.1700
Data Index: 5194445 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2851. Min Range: -1.2851
Max Act: 1.2146. Min Act: -0.1700
Data Index: 2727738 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2851. Min Range: -1.2851
Max Act: 1.1970. Min Act: -0.1700
Data Index: 4905130 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2851. Min Range: -1.2851
Max Act: 1.2146. Min Act: -0.1700
Data Index: 8830099 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2851. Min Range: -1.2851
Max Act: 1.1970. Min Act: -0.1700
Data Index: 3151809 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2851. Min Range: -1.2851
Max Act: 1.1970. Min Act: -0.1700
Data Index: 3378492 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2851. Min Range: -1.2851
Max Act: 1.1970. Min Act: -0.1700
Data Index: 678812 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19