Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3306 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1852. Min Range: -9.1852
Max Act: 9.1852. Min Act: -0.1700
Data Index: 8770750 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1852. Min Range: -9.1852
Max Act: 9.1227. Min Act: -0.1700
Data Index: 7168279 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1852. Min Range: -9.1852
Max Act: 8.8102. Min Act: -0.1700
Data Index: 531872 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1852. Min Range: -9.1852
Max Act: 8.8727. Min Act: -0.1700
Data Index: 491081 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1852. Min Range: -9.1852
Max Act: 8.7477. Min Act: -0.1700
Data Index: 2305197 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1852. Min Range: -9.1852
Max Act: 8.6852. Min Act: -0.1700
Data Index: 6056423 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1852. Min Range: -9.1852
Max Act: 8.6852. Min Act: -0.1700
Data Index: 3515983 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1852. Min Range: -9.1852
Max Act: 8.6227. Min Act: -0.1700
Data Index: 7871414 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1852. Min Range: -9.1852
Max Act: 8.6227. Min Act: -0.1700
Data Index: 6004791 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1852. Min Range: -9.1852
Max Act: 8.6227. Min Act: -0.1700
Data Index: 4807696 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1852. Min Range: -9.1852
Max Act: 8.5602. Min Act: -0.1700
Data Index: 3123440 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1852. Min Range: -9.1852
Max Act: 8.5602. Min Act: -0.1700
Data Index: 7029484 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1852. Min Range: -9.1852
Max Act: 8.4977. Min Act: -0.1700
Data Index: 2365109 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1852. Min Range: -9.1852
Max Act: 8.5602. Min Act: -0.1700
Data Index: 385042 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1852. Min Range: -9.1852
Max Act: 8.4977. Min Act: -0.1700
Data Index: 1698881 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1852. Min Range: -9.1852
Max Act: 8.4977. Min Act: -0.1700
Data Index: 4770703 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1852. Min Range: -9.1852
Max Act: 8.4977. Min Act: -0.1700
Data Index: 7533162 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1852. Min Range: -9.1852
Max Act: 8.4352. Min Act: -0.1700
Data Index: 4141906 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1852. Min Range: -9.1852
Max Act: 8.4352. Min Act: -0.1700
Data Index: 1651924 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1852. Min Range: -9.1852
Max Act: 8.4977. Min Act: -0.1700
Data Index: 4440590 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19