Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1272 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.7247. Min Range: -0.7247
Max Act: 0.7247. Min Act: -0.1700
Data Index: 5832301 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7247. Min Range: -0.7247
Max Act: 0.7165. Min Act: -0.1700
Data Index: 7940221 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7247. Min Range: -0.7247
Max Act: 0.6920. Min Act: -0.1700
Data Index: 5515693 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7247. Min Range: -0.7247
Max Act: 0.6920. Min Act: -0.1700
Data Index: 153261 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7247. Min Range: -0.7247
Max Act: 0.6920. Min Act: -0.1700
Data Index: 5959125 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7247. Min Range: -0.7247
Max Act: 0.6920. Min Act: -0.1700
Data Index: 1479353 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7247. Min Range: -0.7247
Max Act: 0.6920. Min Act: -0.1700
Data Index: 5985310 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7247. Min Range: -0.7247
Max Act: 0.6920. Min Act: -0.1700
Data Index: 7639723 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7247. Min Range: -0.7247
Max Act: 0.6920. Min Act: -0.1700
Data Index: 4915112 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7247. Min Range: -0.7247
Max Act: 0.6920. Min Act: -0.1700
Data Index: 1599035 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7247. Min Range: -0.7247
Max Act: 0.6920. Min Act: -0.1700
Data Index: 2497663 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7247. Min Range: -0.7247
Max Act: 0.6677. Min Act: -0.1700
Data Index: 5045292 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7247. Min Range: -0.7247
Max Act: 0.6596. Min Act: -0.1700
Data Index: 3249054 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7247. Min Range: -0.7247
Max Act: 0.6596. Min Act: -0.1700
Data Index: 2667909 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7247. Min Range: -0.7247
Max Act: 0.6596. Min Act: -0.1700
Data Index: 2402243 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7247. Min Range: -0.7247
Max Act: 0.6596. Min Act: -0.1700
Data Index: 2204130 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7247. Min Range: -0.7247
Max Act: 0.6596. Min Act: -0.1700
Data Index: 2161710 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7247. Min Range: -0.7247
Max Act: 0.6596. Min Act: -0.1700
Data Index: 2082589 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7247. Min Range: -0.7247
Max Act: 0.6596. Min Act: -0.1700
Data Index: 1926337 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7247. Min Range: -0.7247
Max Act: 0.6596. Min Act: -0.1700
Data Index: 1587036 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19